Files
paperclip-docs/docs/connectors/tavily.md
T
d627632874 Release docs for paperclip v2026.1106.0 (#172)
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]>
2026-11-07 13:02:42 +01:00

4.3 KiB

paperclip_version, seo_title, seo_description
paperclip_version seo_title seo_description
v2026.1106.0 Tavily Web Search Connector Give agents web search and page extraction through your Tavily account. Browser sign-in, which Tavily key gets used, the HTTPS callback rule, and fixes.

Tavily

Agents can search the public web and extract the content of pages through Tavily, using your own Tavily account. It suits bounded research tasks where you want the agent to cite where each fact came from.

Tavily appears in the catalog on every instance; no experimental setting is needed.

Before you connect

  • A Tavily account with an API key and some usage allowance. You do not paste the key — sign-in picks it for you — but searches draw on that key's credits.
  • A public HTTPS address for your Paperclip instance. Tavily refuses to send you back to a local http:// address after sign-in, so a Paperclip running only on your own machine cannot complete this setup.

Connect Tavily

  1. Open Connectors and select Tavily.
  2. Read the access line above the main button. It says who the connection belongs to and which agents can use it. To pick a different identity or narrow the agents, select Change.
  3. Select Continue to Tavily and approve access in Tavily's consent screen.

Paperclip registers its client with Tavily automatically and asks for the openid and offline_access scopes. There is nothing to configure in a developer console.

Note: Tavily also documents putting an API key in the server address. Do not use that route; sign-in keeps the key out of the URL.

Choose access

Tavily's server offers read actions only: searching the web and extracting page content. There are no actions that change anything in your Tavily account, which makes this one of the lower-stakes connectors to share.

Two things are still worth deciding:

  • Whose credits. At sign-in, Tavily picks the key named mcp_auth_default if your account has one. Otherwise it may use your personal default key or the first key it finds. Check which key and allowance the connection is using, and if you want to control it, create an mcp_auth_default key before you connect.
  • What agents do with results. Search results are outside content. Ask agents to use focused queries, cite source URLs, and keep what they retrieved separate from what they infer. Research is not permission to contact a company or fill in a form on its site. See Set action permissions.

Try it

Search the web with Tavily for three recent articles about a topic we care about, and list them with their links and a one-line summary each.

Open the links. Results you can check confirm the sign-in and the agent's permission.

Note: Illustrative task, not a recorded test result.

Troubleshooting and limitations

Problem Likely cause Fix
Sign-in is refused before it starts Paperclip is reached over local HTTP Use a public HTTPS address for Paperclip, then connect again
A search fails with a session or request error Tavily's session expired Ask the agent to retry; Paperclip starts a new session but does not replay the failed call on its own
Usage comes from an unexpected key Tavily chose a default key at sign-in Create an mcp_auth_default key in Tavily and reconnect
Searches stop working The key's credits ran out Top up in Tavily
Needs attention The grant was revoked or expired Select Reconnect

Limitations: one Tavily account per connection, browser sign-in only, and public web content only.

Sources