d627632874
Docs for parent release `v2026.1106.0` (`d69631b0`), up from `v2026.1023.0` (`1b4c8038`): 515 parent commits. ## How this branch was built The tag is 914 commits behind what `nightly` has drafted, so this branch isn't cut from `nightly` HEAD. It starts at nightly commit `1952052` (parent `043f2514`), 19 commits before the tag, then adds: - the `main` hotfix (#160) - the sync tooling from `nightly` - docs for those 19 commits Later nightly drafts stay on `nightly`, so no pages had to be removed. No `nightly-draft/*` PRs are open. ## What changed - **Runner by default:** new Claude, Codex, OpenCode and Pi agents start on Paperclip Runner on supported hosts, with **Legacy runner** and **Upgrade runner**. - **Workspaces:** cleanup of finished workspaces, optional Git expiration, and restore points for unsaved work. Restore points are off by default. - **New pages:** Prompt injection prevention, Google Workspace, GitHub Copilot, Speko, Braintrust, Daytona, Ditto and Unikraft. - **Breaking and upgrade notes:** the run history limit, Sentry run failures off by default and the DSN variables, the Docker start command for custom images, `--yes` on `instructions-file:delete`, and slower migrations on large instances. - **Also covered:** project repositories as skill sources, roster bulk edit, Artifacts V1 (experimental, off by default), composer dismissal, `expectedStatusVersion`, `unexecuted_review_stage`, and plugin workspace providers. - **Changelog:** a v2026.1106.0 entry in `reference/changelog.md`. ## Older text corrected These were wrong at the tag, and most are also wrong on the live site: - which permissions let an agent read a peer's configuration or change instructions (`api/agents.md`) - `decideNowCount`, which doesn't exist; the field is `deskBadgeCount` - `file-resources` routes, which are board-only - the **Create project** dialog fields, a CEO rule the code doesn't enforce, and where a terminated agent's reports appear - `instructions-file:put` and `:delete` examples that always failed (`cli/agent.md`) - a curl example that returned `422` (`api/cases.md`) - Google Workspace **Reconnect** instructions, which claimed it reopens the service picker - the `permissionKey` table, which listed 8 of 21 keys - drafting text at the end of `api/agents.md` ## ⚠ Please check these - **Product behaviour that may be a parent bug.** The docs now describe the tag's code, which you may prefer to fix upstream: - The project **Environment** dropdown saves a choice, but runs ignore it (`experimental/environments.md`). - `environments:manage` is granted by roles but no environment route checks it. - `suggest-changes` is documented as agent-only, because only agents have a consent path. Company skill policy decides skill edits. - **Reader-visible mismatches in the parent UI.** The docs follow the code. Upstream copy still mentions a "Built-in agents tab", says Copilot "awaits qualification", and tells people to "Reconnect Google Workspace to change access". ## ⚠ Post-tag leaks removed Nothing to remove from an already-drafted page: post-tag surfaces such as 1Password, Vercel, Supabase deploy, custom gateway onboarding and Artifacts V1 as default never came onto this branch. Authors left out post-tag hunks of the next nightly draft, and the reasons are in the run notes. ## ⚠ Drift None. Zero findings at the tag, from a full parent snapshot. ## ⚠ Verification Failures The tag-accuracy gate reports one leak and nine review entries. None is a real failure: - **Leak:** `reference/cli/service.md`, `paperclipai payload and`. This is a false positive; it's prose from a real message at `cli/src/commands/service.ts:184`. - **Review, 8 new connector pages:** the gate can't confirm new pages. Reviewers confirmed each surface exists at the tag. - **Review, `local_tools`:** an example value from the tag's Runner README. Not provable from code, and kept deliberately: - `sandbox-providers.md` uses `sandbox.yaml`. The tag's README says `install.yaml`, which returned 404 when checked. The upstream fix is post-tag. - The Google Workspace row about older OAuth brokers rests on release notes and a design doc. The broker isn't in this repo. - External claims about provider behaviour (for example Braintrust, Daytona, Unikraft and Google scopes). ## ↻ Renames detected None. The rename helper wasn't run: the 19-commit delta adds no new adapter, skill, or plugin directories that it would check. ## Verification All checks read a checkout pinned to the tag. - **First round:** authors, a release-notes audit, an audit of corrections stranded on `nightly`, an audit of 321 lines the last realign dropped from `main` (about 130 checked directly in code), and six fresh verifiers. - **Second round:** seven new verifiers re-checked every changed area, tracing behaviour rather than matching labels, and fixed about 50 more defects. That volume means more may remain. - **Limits of that second round:** - Each verifier reported what it only string-matched. That includes parts of Artifacts V1, the **Upgrade runner** notice, Copilot run behaviour, and some Plugin SDK contract text. - The second-round fixes themselves weren't reviewed by a third round. - **Gates:** `docs:build`, `docs:test` and `sync:check` pass. - **Nothing was run against a live instance.** All of this comes from reading code. ## Screenshots **196 of 278 screenshots are stale and none were recaptured.** The list is in `SCREENSHOTS_PENDING.md`. Some visibly differ from the text, such as the removed **Run with provider trace** button and the old roster tabs. ## After merge 1. Keep the PR title as is: `tag-docs-release.yml` reads the version from it. 2. Confirm the `docs/v2026.1106.0` tag exists. 3. Run `node scripts/sync/realign-nightly.mjs release/v2026.1106.0 --push`, then audit for dropped lines and duplicated paragraphs, and set `nightly` state back to `branch_mode: nightly`. 4. Check that `docs.paperclip.ing` serves the release: a new page, a new claim, and the changelog's top entry. 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Opus 4.8 (1M context) <[email protected]> Co-authored-by: DevRel Gemini <[email protected]> Co-authored-by: Paperclip <[email protected]> Co-authored-by: Dotta <[email protected]> Co-authored-by: ClaudeCoder <[email protected]>
5.8 KiB
paperclip_version, seo_title, seo_description
| paperclip_version | seo_title | seo_description |
|---|---|---|
| v2026.1106.0 | Zapier Connector | Reach thousands of apps through a Zapier MCP server. The generated URL is a credential — how to set it up safely, choose exposed actions, and troubleshoot. |
Zapier
Zapier lets agents reach the apps you have already connected in your Zapier account. You build an MCP server in Zapier, choose which actions it exposes, and give Paperclip its generated URL.
Danger: The generated Zapier URL contains its own access token. It is a credential, not just an address — anyone who has the URL can call the actions the server exposes. Treat it exactly like a password: never paste it into a ticket, a chat message, a screenshot, or a commit.
Zapier is available on every instance; no experimental setting is required.
Before you connect
- A Zapier account with the apps you want to reach already connected there.
- An MCP server created in Zapier, with the specific actions you want exposed enabled on it.
The actions an agent can call are decided in Zapier, not Paperclip. This is the main thing to get right before connecting: a server with broad actions enabled gives the agent broad reach, and Paperclip cannot narrow it beyond switching off what Zapier advertises.
Connect Zapier
- In Zapier, create an MCP server and enable only the actions agents should have. Start with the smallest useful set.
- Copy the server's complete generated connection URL.
- Open Connectors and select Zapier.
- Read the access line above the main button. It says who the connection signs in as and which agents can use it. To pick a different identity, narrow the agents, or use another sign-in method, select Change.
- Paste the full MCP server URL and select Connect Zapier. Paperclip verifies it can reach the server, then stores the URL as a secret.
Paste the URL exactly as Zapier generated it, including the token portion. A truncated URL fails the check.
Choose access
Two separate layers, and it is worth knowing which one to reach for:
| Layer | Controlled in | Use it to |
|---|---|---|
| Which actions exist at all | Zapier, on the MCP server | Remove capability entirely |
| Whether an agent may call an exposed action | Paperclip, on the Permissions tab | Require approval, or switch one off |
Changing the exposed action set in Zapier does not require reconnecting — use Refresh actions in Paperclip afterwards to re-read the list.
Warning: On this connection, an action you expose in Zapier becomes active in Paperclip once you refresh, governed by the policies already in force rather than held back for approval. Widening the Zapier side is the access decision; review the Paperclip list after every refresh.
Anyone in Zapier who can edit that MCP server can widen what the agent can reach, without touching Paperclip. Keep the list of people who can edit it small, and review it when you review the connection.
Because Zapier actions usually act on real systems — sending messages, creating records — most of them classify as writes. Active actions start as Allowed; change them to Ask first if you want to review calls while learning how the agent uses them. See Set action permissions.
Try it
Choose a deliberately read-only action for the first check — for example looking up a record or listing recent items in a connected app — and run it as the agent you intend to use.
Use Zapier to look up the most recent row in my tracking spreadsheet and tell me what it says. Do not create or send anything.
A read confirms the URL, the server, and the agent's permission without acting on an outside system. Avoid verifying with an action that sends a message or creates a record; Zapier actions usually reach real destinations.
Note: Illustrative task, not a recorded test result. Substitute an action your own server exposes.
Troubleshooting and limitations
| Problem | Likely cause | Fix |
|---|---|---|
| Connect Zapier fails | The URL is incomplete, or the server was deleted in Zapier | Copy the complete URL again from Zapier |
| The action list is empty | No actions are enabled on the Zapier MCP server | Enable actions in Zapier, then Refresh actions |
| An action you enabled in Zapier is missing | Paperclip has not re-read the list | Use Refresh actions |
| An action you exposed in Zapier is missing | Paperclip's copy of the list is stale | Use Refresh actions, then confirm the new action's setting — it arrives active under existing policy rather than switched off |
| An action fails inside Zapier | The underlying app connection in Zapier has expired | Reconnect that app in Zapier |
| You suspect the URL leaked | The URL is a bearer credential | Regenerate the server URL in Zapier and reconnect in Paperclip |
Limitations: the action surface is whatever the Zapier server exposes, and Paperclip cannot see or restrict what happens inside a Zap beyond the action it calls. Zapier's own plan limits and task quotas apply. Rotating the URL means reconnecting.
Related guides
-
Connect your own MCP server — for a server you run yourself.
Sources
- Connection setup — one-screen access choices and setup behavior.
- Remote MCP setup — provider-specific connection controls.