Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-19 14:13:35 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #4483] [BUG]: MCP servers not used by any Ollama Model #2856

New Issue
Closed
opened 2026-02-22 18:31:32 -05:00 by yindo · 2 comments
yindo commented 2026-02-22 18:31:32 -05:00
Owner
Copy Link
Copy Source

Originally created by @danielbjornadal on GitHub (Oct 3, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4483

How are you running AnythingLLM?

Docker (remote machine)

What happened?

I have installed mcp-server-time and mcp-atlassian MCP tool where i use Ollama.

anythingllm_mcp_servers.json: (removed default that where there (... is ofc not included in production)

    {
      "mcpServers": {
       ...
        "mcp-atlassian": {
          "command": "uvx",
          "args": [
            "mcp-atlassian",
            "--jira-url=<removed>",
            "--jira-personal-token=<removed>",
            "--confluence-<removed>",
            "--confluence-personal-token=<removed>"
          ],
        },
        "mcp-server-time": {
          "command": "uvx",
          "args": [
            "mcp-server-time",
            "--local-timezone=Europe/Oslo"
          ],
        }
      }
    }

Models i have tested: gpt-oss:120b, qwen3:32b, llama4:latest

MCP servers shows as ON and list all functions OK.

Image Image Image 
[collector] info: [TikTokenTokenizer] Initialized new TikTokenTokenizer instance.
[collector] info: Collector hot directory and tmp storage wiped!
[collector] info: Document processor app listening on port 8888
Environment variables loaded from .env
Prisma schema loaded from prisma/schema.prisma
✔ Generated Prisma Client (v5.3.1) to ./node_modules/@prisma/client in 610ms
Start using Prisma Client in Node.js (See: https://pris.ly/d/client)
import { PrismaClient } from '@prisma/client'
const prisma = new PrismaClient()
or start using Prisma Client at the edge (See: https://pris.ly/d/accelerate)
import { PrismaClient } from '@prisma/client/edge'
const prisma = new PrismaClient()
See other ways of importing Prisma Client: http://pris.ly/d/importing-client
Environment variables loaded from .env
Prisma schema loaded from prisma/schema.prisma
Datasource "db": SQLite database "anythingllm.db" at "file:../storage/anythingllm.db"
33 migrations found in prisma/migrations
No pending migrations to apply.
┌─────────────────────────────────────────────────────────┐
│  Update available 5.3.1 -> 6.16.3                       │
│                                                         │
│  This is a major update - please follow the guide at    │
│  https://pris.ly/d/major-version-upgrade                │
│                                                         │
│  Run the following to update                            │
│    npm i --save-dev prisma@latest                       │
│    npm i @prisma/client@latest                          │
└─────────────────────────────────────────────────────────┘
[backend] info: [EncryptionManager] Self-assigning key & salt for encrypting arbitrary data.
[backend] info: [TokenManager] Initialized new TokenManager instance for model: gpt-3.5-turbo
[backend] info: [TokenManager] Returning existing instance for model: gpt-3.5-turbo
[backend] info: [TELEMETRY ENABLED] Anonymous Telemetry enabled. Telemetry helps Mintplex Labs Inc improve AnythingLLM.
[backend] info: prisma:info Starting a sqlite pool with 65 connections.
[backend] info: [TELEMETRY SENT] {"event":"server_boot","distinctId":"b1dd2af0-ec1f-4828-9249-1dd398421c94","properties":{"commit":"--","runtime":"docker"}}
[backend] info: [CommunicationKey] RSA key pair generated for signed payloads within AnythingLLM services.
[backend] info: [EncryptionManager] Loaded existing key & salt for encrypting arbitrary data.
[backend] info: [BackgroundWorkerService] Starting...
[backend] info: [BackgroundWorkerService] Service started with 1 jobs ["cleanup-orphan-documents"]
[backend] info: [Ollama] Context windows cached for all models!
[backend] info: ⚡Pre-cached context windows for Ollama
[backend] info: Primary server in HTTP mode listening on port 3001
[backend] info: [MetaGenerator] fetching custom meta tag settings...
[backend] info: [OllamaEmbedder] initialized with model gpt-oss:120b at http://ollama.ollama:11434. num_ctx: 8192
[backend] info: [fillSourceWindow] Need to backfill 4 chunks to fill in the source window for RAG!
[backend] info: [TokenManager] Initialized new TokenManager instance for model: gpt-oss:120b
[backend] info: [Ollama] Context windows cached for all models!
[backend] info: [Ollama] initialized with
model: gpt-oss:120b
perf: base
n_ctx: 8192
[backend] info: [TELEMETRY SENT] {"event":"sent_chat","distinctId":"b1dd2af0-ec1f-4828-9249-1dd398421c94","properties":{"multiUserMode":false,"LLMSelection":"ollama","Embedder":"ollama","VectorDbSelection":"lancedb","multiModal":false,"TTSSelection":"native","LLMModel":"gpt-oss:120b","runtime":"docker"}}
[backend] info: [Event Logged] - sent_chat
[backend] info: [MCPHypervisor] Initializing MCP Hypervisor - subsequent calls will boot faster
[backend] info: [MCPHypervisor] MCP Config File: /app/server/storage/plugins/anythingllm_mcp_servers.json
[backend] info: [MCPHypervisor] Attempting to start MCP server: face-generator
npm warn exec The following package was not found and will be installed: @dasheck0/face-generator@1.0.1
Face Generator MCP server running on stdio
[backend] info: [MCPHypervisor] Attempting to start MCP server: mcp-atlassian
Downloading rapidfuzz (3.0MiB)
Downloading pygments (1.2MiB)
Downloading cryptography (4.3MiB)
Downloading pydantic-core (1.9MiB)
Downloading lxml (5.0MiB)
 Downloaded pydantic-core
 Downloaded rapidfuzz
 Downloaded cryptography
 Downloaded lxml
 Downloaded pygments
Installed 84 packages in 128ms
[10/03/25 12:51:43] INFO     Starting MCP server 'Atlassian MCP'   server.py:734
                             with transport 'stdio'                             
INFO - FastMCP.fastmcp.server.server - Starting MCP server 'Atlassian MCP' with transport 'stdio'
[backend] info: [MCPHypervisor] Attempting to start MCP server: mcp-server-time
Installed 30 packages in 52ms
[backend] info: [MCPHypervisor] Attempting to start MCP server: postgres-http
[backend] info: [MCPHypervisor] Failed to start MCP server: postgres-http {"error":"fetch failed","stack":"TypeError: fetch failed\n    at node:internal/deps/undici/undici:12637:11\n    at process.processTicksAndRejections (node:internal/process/task_queues:95:5)\n    at async StreamableHTTPClientTransport.send (/app/server/node_modules/@modelcontextprotocol/sdk/dist/cjs/client/streamableHttp.js:251:30)"}
[backend] info: [MCPHypervisor] Successfully started 3 MCP servers: ["face-generator","mcp-atlassian","mcp-server-time"]
prisma:info Starting a sqlite pool with 65 connections.
[backend] info: [101:244]: No direct uploads path found - exiting.
[bg-worker][cleanup-orphan-documents] info: [101:244]: No direct uploads path found - exiting.
[backend] warn: Child process exited with code 0 and signal null
[backend] info: Worker for job "cleanup-orphan-documents" exited with code 0
[backend] info: [OllamaEmbedder] initialized with model gpt-oss:120b at http://ollama.ollama:11434. num_ctx: 8192
[backend] info: [fillSourceWindow] Need to backfill 4 chunks to fill in the source window for RAG!
[backend] info: [TokenManager] Returning existing instance for model: gpt-oss:120b
[backend] info: [Ollama] Context windows cached for all models!
[backend] info: [Ollama] initialized with
model: gpt-oss:120b
perf: base
n_ctx: 8192
[backend] info: [Event Logged] - sent_chat
[backend] info: [MCPHypervisor] MCP Servers already running, skipping boot.
[backend] info: [MCPHypervisor] Pruning MCP server: face-generator
[backend] info: [MCPHypervisor] Pruning MCP server: mcp-server-time
[backend] info: [TELEMETRY SENT] {"event":"workspace_thread_created","distinctId":"b1dd2af0-ec1f-4828-9249-1dd398421c94","properties":{"multiUserMode":false,"LLMSelection":"ollama","Embedder":"ollama","VectorDbSelection":"lancedb","TTSSelection":"native","LLMModel":"gpt-oss:120b","runtime":"docker"}}
[backend] info: [Event Logged] - workspace_thread_created
[backend] info: [OllamaEmbedder] initialized with model gpt-oss:120b at http://ollama.ollama:11434. num_ctx: 8192
[backend] info: [fillSourceWindow] Need to backfill 4 chunks to fill in the source window for RAG!
[backend] info: [TokenManager] Returning existing instance for model: gpt-oss:120b
[backend] info: [Ollama] Context windows cached for all models!
[backend] info: [Ollama] initialized with
model: gpt-oss:120b
perf: base
n_ctx: 8192
[backend] info: [Event Logged] - sent_chat
[backend] info: [TELEMETRY SENT] {"event":"workspace_thread_created","distinctId":"b1dd2af0-ec1f-4828-9249-1dd398421c94","properties":{"multiUserMode":false,"LLMSelection":"ollama","Embedder":"ollama","VectorDbSelection":"lancedb","TTSSelection":"native","LLMModel":"gpt-oss:120b","runtime":"docker"}}
[backend] info: [Event Logged] - workspace_thread_created
[backend] info: [OllamaEmbedder] initialized with model gpt-oss:120b at http://ollama.ollama:11434. num_ctx: 8192
[backend] info: [TokenManager] Returning existing instance for model: gpt-oss:120b
[backend] info: [Ollama] Context windows cached for all models!
[backend] info: [Ollama] initialized with
model: gpt-oss:120b
perf: base
n_ctx: 8192
[backend] info: [Event Logged] - sent_chat
[backend] info: [OllamaEmbedder] initialized with model gpt-oss:120b at http://ollama.ollama:11434. num_ctx: 8192
[backend] info: [fillSourceWindow] Need to backfill 4 chunks to fill in the source window for RAG!
[backend] info: [TokenManager] Returning existing instance for model: gpt-oss:120b
[backend] info: [Ollama] Context windows cached for all models!
[backend] info: [Ollama] initialized with
model: gpt-oss:120b
perf: base
n_ctx: 8192
[backend] info: [Event Logged] - sent_chat
[backend] info: [OllamaEmbedder] initialized with model gpt-oss:120b at http://ollama.ollama:11434. num_ctx: 8192
[backend] info: [fillSourceWindow] Need to backfill 4 chunks to fill in the source window for RAG!
[backend] info: [TokenManager] Returning existing instance for model: gpt-oss:120b
[backend] info: [Ollama] Context windows cached for all models!
[backend] info: [Ollama] initialized with
model: gpt-oss:120b
perf: base
n_ctx: 8192
[backend] info: [Event Logged] - sent_chat

Are there known steps to reproduce?

Clean install.
Point towards Ollama
Add MCP

Originally created by @danielbjornadal on GitHub (Oct 3, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4483 ### How are you running AnythingLLM? Docker (remote machine) ### What happened? I have installed mcp-server-time and mcp-atlassian MCP tool where i use Ollama. anythingllm_mcp_servers.json: (removed default that where there (... is ofc not included in production) ``` { "mcpServers": { ... "mcp-atlassian": { "command": "uvx", "args": [ "mcp-atlassian", "--jira-url=<removed>", "--jira-personal-token=<removed>", "--confluence-<removed>", "--confluence-personal-token=<removed>" ], }, "mcp-server-time": { "command": "uvx", "args": [ "mcp-server-time", "--local-timezone=Europe/Oslo" ], } } } ``` Models i have tested: gpt-oss:120b, qwen3:32b, llama4:latest MCP servers shows as ON and list all functions OK. <img width="359" height="97" alt="Image" src="https://github.com/user-attachments/assets/1ea7c806-e075-40e6-8f37-ecadb4afe5ec" /> <img width="813" height="642" alt="Image" src="https://github.com/user-attachments/assets/8fbf65ca-0c4a-4c9e-a1eb-66952472fe89" /> <img width="1156" height="827" alt="Image" src="https://github.com/user-attachments/assets/e69a13f0-4987-4916-ac66-3759fcfef6d2" /> ``` [collector] info: [TikTokenTokenizer] Initialized new TikTokenTokenizer instance. [collector] info: Collector hot directory and tmp storage wiped! [collector] info: Document processor app listening on port 8888 Environment variables loaded from .env Prisma schema loaded from prisma/schema.prisma ✔ Generated Prisma Client (v5.3.1) to ./node_modules/@prisma/client in 610ms Start using Prisma Client in Node.js (See: https://pris.ly/d/client) import { PrismaClient } from '@prisma/client' const prisma = new PrismaClient() or start using Prisma Client at the edge (See: https://pris.ly/d/accelerate) import { PrismaClient } from '@prisma/client/edge' const prisma = new PrismaClient() See other ways of importing Prisma Client: http://pris.ly/d/importing-client Environment variables loaded from .env Prisma schema loaded from prisma/schema.prisma Datasource "db": SQLite database "anythingllm.db" at "file:../storage/anythingllm.db" 33 migrations found in prisma/migrations No pending migrations to apply. ┌─────────────────────────────────────────────────────────┐ │ Update available 5.3.1 -> 6.16.3 │ │ │ │ This is a major update - please follow the guide at │ │ https://pris.ly/d/major-version-upgrade │ │ │ │ Run the following to update │ │ npm i --save-dev prisma@latest │ │ npm i @prisma/client@latest │ └─────────────────────────────────────────────────────────┘ [backend] info: [EncryptionManager] Self-assigning key & salt for encrypting arbitrary data. [backend] info: [TokenManager] Initialized new TokenManager instance for model: gpt-3.5-turbo [backend] info: [TokenManager] Returning existing instance for model: gpt-3.5-turbo [backend] info: [TELEMETRY ENABLED] Anonymous Telemetry enabled. Telemetry helps Mintplex Labs Inc improve AnythingLLM. [backend] info: prisma:info Starting a sqlite pool with 65 connections. [backend] info: [TELEMETRY SENT] {"event":"server_boot","distinctId":"b1dd2af0-ec1f-4828-9249-1dd398421c94","properties":{"commit":"--","runtime":"docker"}} [backend] info: [CommunicationKey] RSA key pair generated for signed payloads within AnythingLLM services. [backend] info: [EncryptionManager] Loaded existing key & salt for encrypting arbitrary data. [backend] info: [BackgroundWorkerService] Starting... [backend] info: [BackgroundWorkerService] Service started with 1 jobs ["cleanup-orphan-documents"] [backend] info: [Ollama] Context windows cached for all models! [backend] info: ⚡Pre-cached context windows for Ollama [backend] info: Primary server in HTTP mode listening on port 3001 [backend] info: [MetaGenerator] fetching custom meta tag settings... [backend] info: [OllamaEmbedder] initialized with model gpt-oss:120b at http://ollama.ollama:11434. num_ctx: 8192 [backend] info: [fillSourceWindow] Need to backfill 4 chunks to fill in the source window for RAG! [backend] info: [TokenManager] Initialized new TokenManager instance for model: gpt-oss:120b [backend] info: [Ollama] Context windows cached for all models! [backend] info: [Ollama] initialized with model: gpt-oss:120b perf: base n_ctx: 8192 [backend] info: [TELEMETRY SENT] {"event":"sent_chat","distinctId":"b1dd2af0-ec1f-4828-9249-1dd398421c94","properties":{"multiUserMode":false,"LLMSelection":"ollama","Embedder":"ollama","VectorDbSelection":"lancedb","multiModal":false,"TTSSelection":"native","LLMModel":"gpt-oss:120b","runtime":"docker"}} [backend] info: [Event Logged] - sent_chat [backend] info: [MCPHypervisor] Initializing MCP Hypervisor - subsequent calls will boot faster [backend] info: [MCPHypervisor] MCP Config File: /app/server/storage/plugins/anythingllm_mcp_servers.json [backend] info: [MCPHypervisor] Attempting to start MCP server: face-generator npm warn exec The following package was not found and will be installed: @dasheck0/face-generator@1.0.1 Face Generator MCP server running on stdio [backend] info: [MCPHypervisor] Attempting to start MCP server: mcp-atlassian Downloading rapidfuzz (3.0MiB) Downloading pygments (1.2MiB) Downloading cryptography (4.3MiB) Downloading pydantic-core (1.9MiB) Downloading lxml (5.0MiB) Downloaded pydantic-core Downloaded rapidfuzz Downloaded cryptography Downloaded lxml Downloaded pygments Installed 84 packages in 128ms [10/03/25 12:51:43] INFO Starting MCP server 'Atlassian MCP' server.py:734 with transport 'stdio' INFO - FastMCP.fastmcp.server.server - Starting MCP server 'Atlassian MCP' with transport 'stdio' [backend] info: [MCPHypervisor] Attempting to start MCP server: mcp-server-time Installed 30 packages in 52ms [backend] info: [MCPHypervisor] Attempting to start MCP server: postgres-http [backend] info: [MCPHypervisor] Failed to start MCP server: postgres-http {"error":"fetch failed","stack":"TypeError: fetch failed\n at node:internal/deps/undici/undici:12637:11\n at process.processTicksAndRejections (node:internal/process/task_queues:95:5)\n at async StreamableHTTPClientTransport.send (/app/server/node_modules/@modelcontextprotocol/sdk/dist/cjs/client/streamableHttp.js:251:30)"} [backend] info: [MCPHypervisor] Successfully started 3 MCP servers: ["face-generator","mcp-atlassian","mcp-server-time"] prisma:info Starting a sqlite pool with 65 connections. [backend] info: [101:244]: No direct uploads path found - exiting. [bg-worker][cleanup-orphan-documents] info: [101:244]: No direct uploads path found - exiting. [backend] warn: Child process exited with code 0 and signal null [backend] info: Worker for job "cleanup-orphan-documents" exited with code 0 [backend] info: [OllamaEmbedder] initialized with model gpt-oss:120b at http://ollama.ollama:11434. num_ctx: 8192 [backend] info: [fillSourceWindow] Need to backfill 4 chunks to fill in the source window for RAG! [backend] info: [TokenManager] Returning existing instance for model: gpt-oss:120b [backend] info: [Ollama] Context windows cached for all models! [backend] info: [Ollama] initialized with model: gpt-oss:120b perf: base n_ctx: 8192 [backend] info: [Event Logged] - sent_chat [backend] info: [MCPHypervisor] MCP Servers already running, skipping boot. [backend] info: [MCPHypervisor] Pruning MCP server: face-generator [backend] info: [MCPHypervisor] Pruning MCP server: mcp-server-time [backend] info: [TELEMETRY SENT] {"event":"workspace_thread_created","distinctId":"b1dd2af0-ec1f-4828-9249-1dd398421c94","properties":{"multiUserMode":false,"LLMSelection":"ollama","Embedder":"ollama","VectorDbSelection":"lancedb","TTSSelection":"native","LLMModel":"gpt-oss:120b","runtime":"docker"}} [backend] info: [Event Logged] - workspace_thread_created [backend] info: [OllamaEmbedder] initialized with model gpt-oss:120b at http://ollama.ollama:11434. num_ctx: 8192 [backend] info: [fillSourceWindow] Need to backfill 4 chunks to fill in the source window for RAG! [backend] info: [TokenManager] Returning existing instance for model: gpt-oss:120b [backend] info: [Ollama] Context windows cached for all models! [backend] info: [Ollama] initialized with model: gpt-oss:120b perf: base n_ctx: 8192 [backend] info: [Event Logged] - sent_chat [backend] info: [TELEMETRY SENT] {"event":"workspace_thread_created","distinctId":"b1dd2af0-ec1f-4828-9249-1dd398421c94","properties":{"multiUserMode":false,"LLMSelection":"ollama","Embedder":"ollama","VectorDbSelection":"lancedb","TTSSelection":"native","LLMModel":"gpt-oss:120b","runtime":"docker"}} [backend] info: [Event Logged] - workspace_thread_created [backend] info: [OllamaEmbedder] initialized with model gpt-oss:120b at http://ollama.ollama:11434. num_ctx: 8192 [backend] info: [TokenManager] Returning existing instance for model: gpt-oss:120b [backend] info: [Ollama] Context windows cached for all models! [backend] info: [Ollama] initialized with model: gpt-oss:120b perf: base n_ctx: 8192 [backend] info: [Event Logged] - sent_chat [backend] info: [OllamaEmbedder] initialized with model gpt-oss:120b at http://ollama.ollama:11434. num_ctx: 8192 [backend] info: [fillSourceWindow] Need to backfill 4 chunks to fill in the source window for RAG! [backend] info: [TokenManager] Returning existing instance for model: gpt-oss:120b [backend] info: [Ollama] Context windows cached for all models! [backend] info: [Ollama] initialized with model: gpt-oss:120b perf: base n_ctx: 8192 [backend] info: [Event Logged] - sent_chat [backend] info: [OllamaEmbedder] initialized with model gpt-oss:120b at http://ollama.ollama:11434. num_ctx: 8192 [backend] info: [fillSourceWindow] Need to backfill 4 chunks to fill in the source window for RAG! [backend] info: [TokenManager] Returning existing instance for model: gpt-oss:120b [backend] info: [Ollama] Context windows cached for all models! [backend] info: [Ollama] initialized with model: gpt-oss:120b perf: base n_ctx: 8192 [backend] info: [Event Logged] - sent_chat ``` ### Are there known steps to reproduce? Clean install. Point towards Ollama Add MCP
yindo added the possible bug label 2026-02-22 18:31:32 -05:00
yindo closed this issue 2026-02-22 18:31:33 -05:00
yindo commented 2026-02-22 18:31:33 -05:00
Author
Owner
Copy Link
Copy Source

@danielbjornadal commented on GitHub (Oct 3, 2025):

Added some debug logging:


Container: anythingllm
Filter
Connected
[collector] info: [TikTokenTokenizer] Initialized new TikTokenTokenizer instance.
[collector] info: Collector hot directory and tmp storage wiped!
[collector] info: Document processor app listening on port 8888
Environment variables loaded from .env
Prisma schema loaded from prisma/schema.prisma
✔ Generated Prisma Client (v5.3.1) to ./node_modules/@prisma/client in 703ms
Start using Prisma Client in Node.js (See: https://pris.ly/d/client)
import { PrismaClient } from '@prisma/client'
const prisma = new PrismaClient()
or start using Prisma Client at the edge (See: https://pris.ly/d/accelerate)
import { PrismaClient } from '@prisma/client/edge'
const prisma = new PrismaClient()
See other ways of importing Prisma Client: http://pris.ly/d/importing-client
Environment variables loaded from .env
Prisma schema loaded from prisma/schema.prisma
Datasource "db": SQLite database "anythingllm.db" at "file:../storage/anythingllm.db"
33 migrations found in prisma/migrations
No pending migrations to apply.
┌─────────────────────────────────────────────────────────┐
│  Update available 5.3.1 -> 6.16.3                       │
│                                                         │
│  This is a major update - please follow the guide at    │
│  https://pris.ly/d/major-version-upgrade                │
│                                                         │
│  Run the following to update                            │
│    npm i --save-dev prisma@latest                       │
│    npm i @prisma/client@latest                          │
└─────────────────────────────────────────────────────────┘
[backend] info: [EncryptionManager] Self-assigning key & salt for encrypting arbitrary data.
[backend] info: [TokenManager] Initialized new TokenManager instance for model: gpt-3.5-turbo
[backend] info: [TokenManager] Returning existing instance for model: gpt-3.5-turbo
[backend] info: [TELEMETRY ENABLED] Anonymous Telemetry enabled. Telemetry helps Mintplex Labs Inc improve AnythingLLM.
[backend] info: prisma:info Starting a sqlite pool with 65 connections.
[backend] info: [TELEMETRY SENT] {"event":"server_boot","distinctId":"b1dd2af0-ec1f-4828-9249-1dd398421c94","properties":{"commit":"--","runtime":"docker"}}
[backend] info: [CommunicationKey] RSA key pair generated for signed payloads within AnythingLLM services.
[backend] info: [EncryptionManager] Loaded existing key & salt for encrypting arbitrary data.
[backend] info: [BackgroundWorkerService] Starting...
[backend] info: [BackgroundWorkerService] Service started with 1 jobs ["cleanup-orphan-documents"]
[backend] info: [Ollama] Context windows cached for all models!
[backend] info: ⚡Pre-cached context windows for Ollama
[backend] info: Primary server in HTTP mode listening on port 3001
[backend] info: [MetaGenerator] fetching custom meta tag settings...
[backend] info: [MCPHypervisor] Initializing MCP Hypervisor - subsequent calls will boot faster
[backend] info: [MCPHypervisor] MCP Config File: /app/server/storage/plugins/anythingllm_mcp_servers.json
[backend] info: [MCPHypervisor] Attempting to start MCP server: mcp-atlassian
Downloading rapidfuzz (3.0MiB)
Downloading cryptography (4.3MiB)
Downloading lxml (5.0MiB)
Downloading pydantic-core (1.9MiB)
Downloading pygments (1.2MiB)
 Downloaded pydantic-core
 Downloaded rapidfuzz
 Downloaded cryptography
 Downloaded lxml
 Downloaded pygments
Installed 84 packages in 116ms
DEBUG - mcp-atlassian - Logging level set to: DEBUG
DEBUG - mcp-atlassian - Logging stream set to: stderr
DEBUG - mcp-atlassian - Attempting to load environment from default .env file if it exists
DEBUG - mcp-atlassian - Final transport determined: stdio
DEBUG - mcp-atlassian - Final port for HTTP transports: 8000
DEBUG - mcp-atlassian - Final host for HTTP transports: 0.0.0.0
DEBUG - mcp-atlassian - Final path for Streamable HTTP: FastMCP default
DEBUG - mcp.server.lowlevel.server - Initializing server 'Confluence MCP Service'
DEBUG - mcp.server.lowlevel.server - Registering handler for ListToolsRequest
DEBUG - mcp.server.lowlevel.server - Registering handler for CallToolRequest
DEBUG - mcp.server.lowlevel.server - Registering handler for ListResourcesRequest
DEBUG - mcp.server.lowlevel.server - Registering handler for ReadResourceRequest
DEBUG - mcp.server.lowlevel.server - Registering handler for PromptListRequest
DEBUG - mcp.server.lowlevel.server - Registering handler for GetPromptRequest
DEBUG - mcp.server.lowlevel.server - Registering handler for ListResourceTemplatesRequest
DEBUG - mcp.server.lowlevel.server - Initializing server 'Jira MCP Service'
DEBUG - mcp.server.lowlevel.server - Registering handler for ListToolsRequest
DEBUG - mcp.server.lowlevel.server - Registering handler for CallToolRequest
DEBUG - mcp.server.lowlevel.server - Registering handler for ListResourcesRequest
DEBUG - mcp.server.lowlevel.server - Registering handler for ReadResourceRequest
DEBUG - mcp.server.lowlevel.server - Registering handler for PromptListRequest
DEBUG - mcp.server.lowlevel.server - Registering handler for GetPromptRequest
DEBUG - mcp.server.lowlevel.server - Registering handler for ListResourceTemplatesRequest
DEBUG - mcp.server.lowlevel.server - Initializing server 'Atlassian MCP'
DEBUG - mcp.server.lowlevel.server - Registering handler for ListToolsRequest
DEBUG - mcp.server.lowlevel.server - Registering handler for CallToolRequest
DEBUG - mcp.server.lowlevel.server - Registering handler for ListResourcesRequest
DEBUG - mcp.server.lowlevel.server - Registering handler for ReadResourceRequest
DEBUG - mcp.server.lowlevel.server - Registering handler for PromptListRequest
DEBUG - mcp.server.lowlevel.server - Registering handler for GetPromptRequest
DEBUG - mcp.server.lowlevel.server - Registering handler for ListResourceTemplatesRequest
INFO - mcp-atlassian.server.main - Added /healthz endpoint for Kubernetes probes
INFO - mcp-atlassian - Starting server with STDIO transport.
DEBUG - mcp-atlassian.utils.lifecycle - SIGPIPE handler registered
DEBUG - mcp-atlassian - STDIO transport detected, setting up stdin monitoring
DEBUG - mcp-atlassian - Starting asyncio event loop...
DEBUG - asyncio - Using selector: EpollSelector
[10/03/25 13:05:41] INFO     Starting MCP server 'Atlassian MCP'   server.py:734
                             with transport 'stdio'                             
INFO - FastMCP.fastmcp.server.server - Starting MCP server 'Atlassian MCP' with transport 'stdio'
INFO - mcp-atlassian.server.main - Main Atlassian MCP server lifespan starting...
INFO - mcp-atlassian.utils.environment - Using Confluence Server/Data Center authentication (PAT or Basic Auth)
INFO - mcp-atlassian.utils.environment - Using Jira Server/Data Center authentication (PAT or Basic Auth)
DEBUG - mcp_atlassian.utils.tools - ENABLED_TOOLS environment variable not set or empty.
INFO - mcp-atlassian.server.main - Jira configuration loaded and authentication is configured.
INFO - mcp-atlassian.server.main - Confluence configuration loaded and authentication is configured.
INFO - mcp-atlassian.server.main - Read-only mode: ENABLED
INFO - mcp-atlassian.server.main - Enabled tools filter: All tools enabled
[backend] info: [MCPHypervisor] Attempting to start MCP server: mcp-server-time
DEBUG - mcp.server.lowlevel.server - Received message: root=InitializedNotification(method='notifications/initialized', params=None, jsonrpc='2.0')
Installed 30 packages in 50ms
[backend] info: [MCPHypervisor] Successfully started 2 MCP servers: ["mcp-atlassian","mcp-server-time"]
DEBUG - mcp.server.lowlevel.server - Received message: <mcp.shared.session.RequestResponder object at 0x7ffab2a86710>
INFO - mcp.server.lowlevel.server - Processing request of type PingRequest
DEBUG - mcp.server.lowlevel.server - Dispatching request of type PingRequest
DEBUG - mcp.server.lowlevel.server - Response sent
DEBUG - mcp.server.lowlevel.server - Received message: <mcp.shared.session.RequestResponder object at 0x7ffab2a854e0>
INFO - mcp.server.lowlevel.server - Processing request of type ListToolsRequest
DEBUG - mcp.server.lowlevel.server - Dispatching request of type ListToolsRequest
DEBUG - mcp-atlassian.server.main - _main_mcp_list_tools: read_only=True, enabled_tools_filter=None
DEBUG - mcp-atlassian.server.main - Aggregated 42 tools before filtering: ['jira_get_user_profile', 'jira_get_issue', 'jira_search', 'jira_search_fields', 'jira_get_project_issues', 'jira_get_transitions', 'jira_get_worklog', 'jira_download_attachments', 'jira_get_agile_boards', 'jira_get_board_issues', 'jira_get_sprints_from_board', 'jira_get_sprint_issues', 'jira_get_link_types', 'jira_create_issue', 'jira_batch_create_issues', 'jira_batch_get_changelogs', 'jira_update_issue', 'jira_delete_issue', 'jira_add_comment', 'jira_add_worklog', 'jira_link_to_epic', 'jira_create_issue_link', 'jira_create_remote_issue_link', 'jira_remove_issue_link', 'jira_transition_issue', 'jira_create_sprint', 'jira_update_sprint', 'jira_get_project_versions', 'jira_get_all_projects', 'jira_create_version', 'jira_batch_create_versions', 'confluence_search', 'confluence_get_page', 'confluence_get_page_children', 'confluence_get_comments', 'confluence_get_labels', 'confluence_add_label', 'confluence_create_page', 'confluence_update_page', 'confluence_delete_page', 'confluence_add_comment', 'confluence_search_user']
DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_get_user_profile' because enabled_tools filter is None.
DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_get_issue' because enabled_tools filter is None.
DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_search' because enabled_tools filter is None.
DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_search_fields' because enabled_tools filter is None.
DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_get_project_issues' because enabled_tools filter is None.
DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_get_transitions' because enabled_tools filter is None.
DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_get_worklog' because enabled_tools filter is None.
DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_download_attachments' because enabled_tools filter is None.
DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_get_agile_boards' because enabled_tools filter is None.
DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_get_board_issues' because enabled_tools filter is None.
DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_get_sprints_from_board' because enabled_tools filter is None.
DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_get_sprint_issues' because enabled_tools filter is None.
DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_get_link_types' because enabled_tools filter is None.
DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_create_issue' because enabled_tools filter is None.
DEBUG - mcp-atlassian.server.main - Excluding tool 'jira_create_issue' due to read-only mode and 'write' tag
DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_batch_create_issues' because enabled_tools filter is None.
DEBUG - mcp-atlassian.server.main - Excluding tool 'jira_batch_create_issues' due to read-only mode and 'write' tag
DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_batch_get_changelogs' because enabled_tools filter is None.
DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_update_issue' because enabled_tools filter is None.
DEBUG - mcp-atlassian.server.main - Excluding tool 'jira_update_issue' due to read-only mode and 'write' tag
DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_delete_issue' because enabled_tools filter is None.
DEBUG - mcp-atlassian.server.main - Excluding tool 'jira_delete_issue' due to read-only mode and 'write' tag
DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_add_comment' because enabled_tools filter is None.
DEBUG - mcp-atlassian.server.main - Excluding tool 'jira_add_comment' due to read-only mode and 'write' tag
DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_add_worklog' because enabled_tools filter is None.
DEBUG - mcp-atlassian.server.main - Excluding tool 'jira_add_worklog' due to read-only mode and 'write' tag
DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_link_to_epic' because enabled_tools filter is None.
DEBUG - mcp-atlassian.server.main - Excluding tool 'jira_link_to_epic' due to read-only mode and 'write' tag
DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_create_issue_link' because enabled_tools filter is None.
DEBUG - mcp-atlassian.server.main - Excluding tool 'jira_create_issue_link' due to read-only mode and 'write' tag
DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_create_remote_issue_link' because enabled_tools filter is None.
DEBUG - mcp-atlassian.server.main - Excluding tool 'jira_create_remote_issue_link' due to read-only mode and 'write' tag
DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_remove_issue_link' because enabled_tools filter is None.
DEBUG - mcp-atlassian.server.main - Excluding tool 'jira_remove_issue_link' due to read-only mode and 'write' tag
DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_transition_issue' because enabled_tools filter is None.
DEBUG - mcp-atlassian.server.main - Excluding tool 'jira_transition_issue' due to read-only mode and 'write' tag
DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_create_sprint' because enabled_tools filter is None.
DEBUG - mcp-atlassian.server.main - Excluding tool 'jira_create_sprint' due to read-only mode and 'write' tag
DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_update_sprint' because enabled_tools filter is None.
DEBUG - mcp-atlassian.server.main - Excluding tool 'jira_update_sprint' due to read-only mode and 'write' tag
DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_get_project_versions' because enabled_tools filter is None.
DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_get_all_projects' because enabled_tools filter is None.
DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_create_version' because enabled_tools filter is None.
DEBUG - mcp-atlassian.server.main - Excluding tool 'jira_create_version' due to read-only mode and 'write' tag
DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_batch_create_versions' because enabled_tools filter is None.
DEBUG - mcp-atlassian.server.main - Excluding tool 'jira_batch_create_versions' due to read-only mode and 'write' tag
DEBUG - mcp_atlassian.utils.tools - Including tool 'confluence_search' because enabled_tools filter is None.
DEBUG - mcp_atlassian.utils.tools - Including tool 'confluence_get_page' because enabled_tools filter is None.
DEBUG - mcp_atlassian.utils.tools - Including tool 'confluence_get_page_children' because enabled_tools filter is None.
DEBUG - mcp_atlassian.utils.tools - Including tool 'confluence_get_comments' because enabled_tools filter is None.
DEBUG - mcp_atlassian.utils.tools - Including tool 'confluence_get_labels' because enabled_tools filter is None.
DEBUG - mcp_atlassian.utils.tools - Including tool 'confluence_add_label' because enabled_tools filter is None.
DEBUG - mcp-atlassian.server.main - Excluding tool 'confluence_add_label' due to read-only mode and 'write' tag
DEBUG - mcp_atlassian.utils.tools - Including tool 'confluence_create_page' because enabled_tools filter is None.
DEBUG - mcp-atlassian.server.main - Excluding tool 'confluence_create_page' due to read-only mode and 'write' tag
DEBUG - mcp_atlassian.utils.tools - Including tool 'confluence_update_page' because enabled_tools filter is None.
DEBUG - mcp-atlassian.server.main - Excluding tool 'confluence_update_page' due to read-only mode and 'write' tag
DEBUG - mcp_atlassian.utils.tools - Including tool 'confluence_delete_page' because enabled_tools filter is None.
DEBUG - mcp-atlassian.server.main - Excluding tool 'confluence_delete_page' due to read-only mode and 'write' tag
DEBUG - mcp_atlassian.utils.tools - Including tool 'confluence_add_comment' because enabled_tools filter is None.
DEBUG - mcp-atlassian.server.main - Excluding tool 'confluence_add_comment' due to read-only mode and 'write' tag
DEBUG - mcp_atlassian.utils.tools - Including tool 'confluence_search_user' because enabled_tools filter is None.
DEBUG - mcp-atlassian.server.main - _main_mcp_list_tools: Total tools after filtering: 22
DEBUG - mcp.server.lowlevel.server - Response sent
prisma:info Starting a sqlite pool with 65 connections.
[backend] info: [101:209]: No direct uploads path found - exiting.
[bg-worker][cleanup-orphan-documents] info: [101:209]: No direct uploads path found - exiting.
[backend] warn: Child process exited with code 0 and signal null
[backend] info: Worker for job "cleanup-orphan-documents" exited with code 0
[backend] info: [TELEMETRY SENT] {"event":"workspace_thread_created","distinctId":"b1dd2af0-ec1f-4828-9249-1dd398421c94","properties":{"multiUserMode":false,"LLMSelection":"ollama","Embedder":"ollama","VectorDbSelection":"lancedb","TTSSelection":"native","LLMModel":"gpt-oss:120b","runtime":"docker"}}
[backend] info: [Event Logged] - workspace_thread_created
@danielbjornadal commented on GitHub (Oct 3, 2025): Added some debug logging: ``` Container: anythingllm Filter Connected [collector] info: [TikTokenTokenizer] Initialized new TikTokenTokenizer instance. [collector] info: Collector hot directory and tmp storage wiped! [collector] info: Document processor app listening on port 8888 Environment variables loaded from .env Prisma schema loaded from prisma/schema.prisma ✔ Generated Prisma Client (v5.3.1) to ./node_modules/@prisma/client in 703ms Start using Prisma Client in Node.js (See: https://pris.ly/d/client) import { PrismaClient } from '@prisma/client' const prisma = new PrismaClient() or start using Prisma Client at the edge (See: https://pris.ly/d/accelerate) import { PrismaClient } from '@prisma/client/edge' const prisma = new PrismaClient() See other ways of importing Prisma Client: http://pris.ly/d/importing-client Environment variables loaded from .env Prisma schema loaded from prisma/schema.prisma Datasource "db": SQLite database "anythingllm.db" at "file:../storage/anythingllm.db" 33 migrations found in prisma/migrations No pending migrations to apply. ┌─────────────────────────────────────────────────────────┐ │ Update available 5.3.1 -> 6.16.3 │ │ │ │ This is a major update - please follow the guide at │ │ https://pris.ly/d/major-version-upgrade │ │ │ │ Run the following to update │ │ npm i --save-dev prisma@latest │ │ npm i @prisma/client@latest │ └─────────────────────────────────────────────────────────┘ [backend] info: [EncryptionManager] Self-assigning key & salt for encrypting arbitrary data. [backend] info: [TokenManager] Initialized new TokenManager instance for model: gpt-3.5-turbo [backend] info: [TokenManager] Returning existing instance for model: gpt-3.5-turbo [backend] info: [TELEMETRY ENABLED] Anonymous Telemetry enabled. Telemetry helps Mintplex Labs Inc improve AnythingLLM. [backend] info: prisma:info Starting a sqlite pool with 65 connections. [backend] info: [TELEMETRY SENT] {"event":"server_boot","distinctId":"b1dd2af0-ec1f-4828-9249-1dd398421c94","properties":{"commit":"--","runtime":"docker"}} [backend] info: [CommunicationKey] RSA key pair generated for signed payloads within AnythingLLM services. [backend] info: [EncryptionManager] Loaded existing key & salt for encrypting arbitrary data. [backend] info: [BackgroundWorkerService] Starting... [backend] info: [BackgroundWorkerService] Service started with 1 jobs ["cleanup-orphan-documents"] [backend] info: [Ollama] Context windows cached for all models! [backend] info: ⚡Pre-cached context windows for Ollama [backend] info: Primary server in HTTP mode listening on port 3001 [backend] info: [MetaGenerator] fetching custom meta tag settings... [backend] info: [MCPHypervisor] Initializing MCP Hypervisor - subsequent calls will boot faster [backend] info: [MCPHypervisor] MCP Config File: /app/server/storage/plugins/anythingllm_mcp_servers.json [backend] info: [MCPHypervisor] Attempting to start MCP server: mcp-atlassian Downloading rapidfuzz (3.0MiB) Downloading cryptography (4.3MiB) Downloading lxml (5.0MiB) Downloading pydantic-core (1.9MiB) Downloading pygments (1.2MiB) Downloaded pydantic-core Downloaded rapidfuzz Downloaded cryptography Downloaded lxml Downloaded pygments Installed 84 packages in 116ms DEBUG - mcp-atlassian - Logging level set to: DEBUG DEBUG - mcp-atlassian - Logging stream set to: stderr DEBUG - mcp-atlassian - Attempting to load environment from default .env file if it exists DEBUG - mcp-atlassian - Final transport determined: stdio DEBUG - mcp-atlassian - Final port for HTTP transports: 8000 DEBUG - mcp-atlassian - Final host for HTTP transports: 0.0.0.0 DEBUG - mcp-atlassian - Final path for Streamable HTTP: FastMCP default DEBUG - mcp.server.lowlevel.server - Initializing server 'Confluence MCP Service' DEBUG - mcp.server.lowlevel.server - Registering handler for ListToolsRequest DEBUG - mcp.server.lowlevel.server - Registering handler for CallToolRequest DEBUG - mcp.server.lowlevel.server - Registering handler for ListResourcesRequest DEBUG - mcp.server.lowlevel.server - Registering handler for ReadResourceRequest DEBUG - mcp.server.lowlevel.server - Registering handler for PromptListRequest DEBUG - mcp.server.lowlevel.server - Registering handler for GetPromptRequest DEBUG - mcp.server.lowlevel.server - Registering handler for ListResourceTemplatesRequest DEBUG - mcp.server.lowlevel.server - Initializing server 'Jira MCP Service' DEBUG - mcp.server.lowlevel.server - Registering handler for ListToolsRequest DEBUG - mcp.server.lowlevel.server - Registering handler for CallToolRequest DEBUG - mcp.server.lowlevel.server - Registering handler for ListResourcesRequest DEBUG - mcp.server.lowlevel.server - Registering handler for ReadResourceRequest DEBUG - mcp.server.lowlevel.server - Registering handler for PromptListRequest DEBUG - mcp.server.lowlevel.server - Registering handler for GetPromptRequest DEBUG - mcp.server.lowlevel.server - Registering handler for ListResourceTemplatesRequest DEBUG - mcp.server.lowlevel.server - Initializing server 'Atlassian MCP' DEBUG - mcp.server.lowlevel.server - Registering handler for ListToolsRequest DEBUG - mcp.server.lowlevel.server - Registering handler for CallToolRequest DEBUG - mcp.server.lowlevel.server - Registering handler for ListResourcesRequest DEBUG - mcp.server.lowlevel.server - Registering handler for ReadResourceRequest DEBUG - mcp.server.lowlevel.server - Registering handler for PromptListRequest DEBUG - mcp.server.lowlevel.server - Registering handler for GetPromptRequest DEBUG - mcp.server.lowlevel.server - Registering handler for ListResourceTemplatesRequest INFO - mcp-atlassian.server.main - Added /healthz endpoint for Kubernetes probes INFO - mcp-atlassian - Starting server with STDIO transport. DEBUG - mcp-atlassian.utils.lifecycle - SIGPIPE handler registered DEBUG - mcp-atlassian - STDIO transport detected, setting up stdin monitoring DEBUG - mcp-atlassian - Starting asyncio event loop... DEBUG - asyncio - Using selector: EpollSelector [10/03/25 13:05:41] INFO Starting MCP server 'Atlassian MCP' server.py:734 with transport 'stdio' INFO - FastMCP.fastmcp.server.server - Starting MCP server 'Atlassian MCP' with transport 'stdio' INFO - mcp-atlassian.server.main - Main Atlassian MCP server lifespan starting... INFO - mcp-atlassian.utils.environment - Using Confluence Server/Data Center authentication (PAT or Basic Auth) INFO - mcp-atlassian.utils.environment - Using Jira Server/Data Center authentication (PAT or Basic Auth) DEBUG - mcp_atlassian.utils.tools - ENABLED_TOOLS environment variable not set or empty. INFO - mcp-atlassian.server.main - Jira configuration loaded and authentication is configured. INFO - mcp-atlassian.server.main - Confluence configuration loaded and authentication is configured. INFO - mcp-atlassian.server.main - Read-only mode: ENABLED INFO - mcp-atlassian.server.main - Enabled tools filter: All tools enabled [backend] info: [MCPHypervisor] Attempting to start MCP server: mcp-server-time DEBUG - mcp.server.lowlevel.server - Received message: root=InitializedNotification(method='notifications/initialized', params=None, jsonrpc='2.0') Installed 30 packages in 50ms [backend] info: [MCPHypervisor] Successfully started 2 MCP servers: ["mcp-atlassian","mcp-server-time"] DEBUG - mcp.server.lowlevel.server - Received message: <mcp.shared.session.RequestResponder object at 0x7ffab2a86710> INFO - mcp.server.lowlevel.server - Processing request of type PingRequest DEBUG - mcp.server.lowlevel.server - Dispatching request of type PingRequest DEBUG - mcp.server.lowlevel.server - Response sent DEBUG - mcp.server.lowlevel.server - Received message: <mcp.shared.session.RequestResponder object at 0x7ffab2a854e0> INFO - mcp.server.lowlevel.server - Processing request of type ListToolsRequest DEBUG - mcp.server.lowlevel.server - Dispatching request of type ListToolsRequest DEBUG - mcp-atlassian.server.main - _main_mcp_list_tools: read_only=True, enabled_tools_filter=None DEBUG - mcp-atlassian.server.main - Aggregated 42 tools before filtering: ['jira_get_user_profile', 'jira_get_issue', 'jira_search', 'jira_search_fields', 'jira_get_project_issues', 'jira_get_transitions', 'jira_get_worklog', 'jira_download_attachments', 'jira_get_agile_boards', 'jira_get_board_issues', 'jira_get_sprints_from_board', 'jira_get_sprint_issues', 'jira_get_link_types', 'jira_create_issue', 'jira_batch_create_issues', 'jira_batch_get_changelogs', 'jira_update_issue', 'jira_delete_issue', 'jira_add_comment', 'jira_add_worklog', 'jira_link_to_epic', 'jira_create_issue_link', 'jira_create_remote_issue_link', 'jira_remove_issue_link', 'jira_transition_issue', 'jira_create_sprint', 'jira_update_sprint', 'jira_get_project_versions', 'jira_get_all_projects', 'jira_create_version', 'jira_batch_create_versions', 'confluence_search', 'confluence_get_page', 'confluence_get_page_children', 'confluence_get_comments', 'confluence_get_labels', 'confluence_add_label', 'confluence_create_page', 'confluence_update_page', 'confluence_delete_page', 'confluence_add_comment', 'confluence_search_user'] DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_get_user_profile' because enabled_tools filter is None. DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_get_issue' because enabled_tools filter is None. DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_search' because enabled_tools filter is None. DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_search_fields' because enabled_tools filter is None. DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_get_project_issues' because enabled_tools filter is None. DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_get_transitions' because enabled_tools filter is None. DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_get_worklog' because enabled_tools filter is None. DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_download_attachments' because enabled_tools filter is None. DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_get_agile_boards' because enabled_tools filter is None. DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_get_board_issues' because enabled_tools filter is None. DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_get_sprints_from_board' because enabled_tools filter is None. DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_get_sprint_issues' because enabled_tools filter is None. DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_get_link_types' because enabled_tools filter is None. DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_create_issue' because enabled_tools filter is None. DEBUG - mcp-atlassian.server.main - Excluding tool 'jira_create_issue' due to read-only mode and 'write' tag DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_batch_create_issues' because enabled_tools filter is None. DEBUG - mcp-atlassian.server.main - Excluding tool 'jira_batch_create_issues' due to read-only mode and 'write' tag DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_batch_get_changelogs' because enabled_tools filter is None. DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_update_issue' because enabled_tools filter is None. DEBUG - mcp-atlassian.server.main - Excluding tool 'jira_update_issue' due to read-only mode and 'write' tag DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_delete_issue' because enabled_tools filter is None. DEBUG - mcp-atlassian.server.main - Excluding tool 'jira_delete_issue' due to read-only mode and 'write' tag DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_add_comment' because enabled_tools filter is None. DEBUG - mcp-atlassian.server.main - Excluding tool 'jira_add_comment' due to read-only mode and 'write' tag DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_add_worklog' because enabled_tools filter is None. DEBUG - mcp-atlassian.server.main - Excluding tool 'jira_add_worklog' due to read-only mode and 'write' tag DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_link_to_epic' because enabled_tools filter is None. DEBUG - mcp-atlassian.server.main - Excluding tool 'jira_link_to_epic' due to read-only mode and 'write' tag DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_create_issue_link' because enabled_tools filter is None. DEBUG - mcp-atlassian.server.main - Excluding tool 'jira_create_issue_link' due to read-only mode and 'write' tag DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_create_remote_issue_link' because enabled_tools filter is None. DEBUG - mcp-atlassian.server.main - Excluding tool 'jira_create_remote_issue_link' due to read-only mode and 'write' tag DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_remove_issue_link' because enabled_tools filter is None. DEBUG - mcp-atlassian.server.main - Excluding tool 'jira_remove_issue_link' due to read-only mode and 'write' tag DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_transition_issue' because enabled_tools filter is None. DEBUG - mcp-atlassian.server.main - Excluding tool 'jira_transition_issue' due to read-only mode and 'write' tag DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_create_sprint' because enabled_tools filter is None. DEBUG - mcp-atlassian.server.main - Excluding tool 'jira_create_sprint' due to read-only mode and 'write' tag DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_update_sprint' because enabled_tools filter is None. DEBUG - mcp-atlassian.server.main - Excluding tool 'jira_update_sprint' due to read-only mode and 'write' tag DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_get_project_versions' because enabled_tools filter is None. DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_get_all_projects' because enabled_tools filter is None. DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_create_version' because enabled_tools filter is None. DEBUG - mcp-atlassian.server.main - Excluding tool 'jira_create_version' due to read-only mode and 'write' tag DEBUG - mcp_atlassian.utils.tools - Including tool 'jira_batch_create_versions' because enabled_tools filter is None. DEBUG - mcp-atlassian.server.main - Excluding tool 'jira_batch_create_versions' due to read-only mode and 'write' tag DEBUG - mcp_atlassian.utils.tools - Including tool 'confluence_search' because enabled_tools filter is None. DEBUG - mcp_atlassian.utils.tools - Including tool 'confluence_get_page' because enabled_tools filter is None. DEBUG - mcp_atlassian.utils.tools - Including tool 'confluence_get_page_children' because enabled_tools filter is None. DEBUG - mcp_atlassian.utils.tools - Including tool 'confluence_get_comments' because enabled_tools filter is None. DEBUG - mcp_atlassian.utils.tools - Including tool 'confluence_get_labels' because enabled_tools filter is None. DEBUG - mcp_atlassian.utils.tools - Including tool 'confluence_add_label' because enabled_tools filter is None. DEBUG - mcp-atlassian.server.main - Excluding tool 'confluence_add_label' due to read-only mode and 'write' tag DEBUG - mcp_atlassian.utils.tools - Including tool 'confluence_create_page' because enabled_tools filter is None. DEBUG - mcp-atlassian.server.main - Excluding tool 'confluence_create_page' due to read-only mode and 'write' tag DEBUG - mcp_atlassian.utils.tools - Including tool 'confluence_update_page' because enabled_tools filter is None. DEBUG - mcp-atlassian.server.main - Excluding tool 'confluence_update_page' due to read-only mode and 'write' tag DEBUG - mcp_atlassian.utils.tools - Including tool 'confluence_delete_page' because enabled_tools filter is None. DEBUG - mcp-atlassian.server.main - Excluding tool 'confluence_delete_page' due to read-only mode and 'write' tag DEBUG - mcp_atlassian.utils.tools - Including tool 'confluence_add_comment' because enabled_tools filter is None. DEBUG - mcp-atlassian.server.main - Excluding tool 'confluence_add_comment' due to read-only mode and 'write' tag DEBUG - mcp_atlassian.utils.tools - Including tool 'confluence_search_user' because enabled_tools filter is None. DEBUG - mcp-atlassian.server.main - _main_mcp_list_tools: Total tools after filtering: 22 DEBUG - mcp.server.lowlevel.server - Response sent prisma:info Starting a sqlite pool with 65 connections. [backend] info: [101:209]: No direct uploads path found - exiting. [bg-worker][cleanup-orphan-documents] info: [101:209]: No direct uploads path found - exiting. [backend] warn: Child process exited with code 0 and signal null [backend] info: Worker for job "cleanup-orphan-documents" exited with code 0 [backend] info: [TELEMETRY SENT] {"event":"workspace_thread_created","distinctId":"b1dd2af0-ec1f-4828-9249-1dd398421c94","properties":{"multiUserMode":false,"LLMSelection":"ollama","Embedder":"ollama","VectorDbSelection":"lancedb","TTSSelection":"native","LLMModel":"gpt-oss:120b","runtime":"docker"}} [backend] info: [Event Logged] - workspace_thread_created ```
yindo commented 2026-02-22 18:31:33 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Oct 3, 2025):

Use @agent to invoke tools so the model can see them. The default chat is basically RAG only without tools.
Brief overview about why AnythingLLM is like this for now.

  • AnythingLLM existed before agents/function calling even was a thing
  • AnythingLLM existed right when RAG became a thing.
  • AnythingLLM initially was built for RAG use cases, then local models

Agents/tool-calling then became popular; however these models were slow, context windows were limited and 80% of models could not even use tools. Since we like to optimize for small models/low-end hardware users, we made @agent a thing. This made the injection (and context occupied by tool calls) an optional experience instead of mandatory. Add this on top of the fact that for the majority of tool-callings' existence, you could not even stream while using them. This lead to a very long "waiting" period for a response and for SLMs on low-hardware - it was unbearable.

This has been the case forever now. However, models are now smaller with larger contexts, hardware has improved and commoditized, and eventually workspaces will be agentic by default, now having to opt-out of tool calling.

PR: #4279 overhauled this and made agent calling more snappy (will be in next desktop release)
#3483 Will make Workspaces agentic by default, needing to swap back to the normal rag + @agent mode in the future.

Related docs; https://docs.anythingllm.com/agent-not-using-tools

@timothycarambat commented on GitHub (Oct 3, 2025): Use `@agent` to invoke tools so the model can see them. The default chat is basically RAG only without tools. Brief overview about why AnythingLLM is like this _for now_. - AnythingLLM existed before agents/function calling even was a thing - AnythingLLM existed right when RAG became a thing. - AnythingLLM initially was built for RAG use cases, then local models Agents/tool-calling then became popular; however these models were slow, context windows were limited and 80% of models could not even use tools. Since we like to optimize for small models/low-end hardware users, we made `@agent` a thing. This made the injection (and context occupied by tool calls) an _optional_ experience instead of mandatory. Add this on top of the fact that for the majority of tool-callings' existence, you _could not even stream_ while using them. This lead to a very long "waiting" period for a response and for SLMs on low-hardware - it was unbearable. This has been the case forever now. However, models are now smaller with larger contexts, hardware has improved and commoditized, and eventually workspaces will be agentic by default, now having to _opt-out_ of tool calling. PR: #4279 overhauled this and made agent calling more snappy (will be in next desktop release) #3483 Will make Workspaces agentic by default, needing to swap back to the normal rag + `@agent` mode in the future. Related docs; https://docs.anythingllm.com/agent-not-using-tools
yindo changed title from [BUG]: MCP servers not used by any Ollama Model to [GH-ISSUE #4483] [BUG]: MCP servers not used by any Ollama Model 2026-06-05 14:48:54 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Desktop
Docker
Integration Request
Integration Request
OS: Linux
OS: Mobile
OS: Windows
UI/UX
blocked
bug
bug
core-team-only
documentation
duplicate
embed-widget
enhancement
feature request
github_actions
good first issue
investigating
needs info / can't replicate
possible bug
pull-request
Mirrored from GitHub Pull Request
 question
stage: specifications
wontfix
No Label possible bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#2856
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?