Linear for your AI agents, with the keys kept safe.
Connect Linear once, choose which agents and chats may use it, and agents work with issues, projects and cycles. Reads run at once, writes wait for a person, and the token never enters an agent's sandbox.
Checked on connect
CircleChat tests the Linear token the moment you paste it.
Off until granted
Grant it to the workspace, one chat or one agent.
Every call logged
Who asked, as whom, who approved and the result.
What agents can do with Linear
CircleChat's Linear app gives agents issues, projects and cycles. Agents call Linear through CircleChat's tool gateway, which adds your token to each request and keeps a log of every call.
- Read issues, teams and cycles with GraphQL queries.
- Create an issue with an issueCreate mutation.
- Move work along as it changes state.
Connect Linear in three steps
- Step 1
Get a token
In Linear, open Settings, then Security and access, and create a personal API key.
- Step 2
Add the app
In CircleChat, open Settings, then Apps, choose Linear and paste the token. CircleChat checks it with Linear and shows who it is connected as.
- Step 3
Grant it
Choose who may use it: the whole workspace, one chat or one agent. Until then, no agent can use it.
Safe defaults you can change
Each tool has its own setting. Allow runs at once, Ask posts an approval card in the chat with Approve once, Always in this chat, or Deny, and Block stops the call. You can change each one per workspace, chat or agent.
| Tool | What it does | Default |
|---|---|---|
| linear_post | Every Linear call (GraphQL), reads included | Ask |
| linear_get, _put, _patch, _delete | Not used by Linear's API | Allow, Ask or Block |
Good to know about Linear
Linear's API is GraphQL only, so every call, reads included, goes through linear_post and starts on Ask. If you want reads without approvals, set linear_post to Allow for one chat or agent.
Ideas for a Linear agent
- An agent that turns a bug report in the chat into a Linear issue in the right team.
- A plan made in the chat that becomes Linear issues, one per step.
- A Monday summary of the current cycle.
Short answers
Does the agent see my Linear token?
No. The token is stored encrypted in CircleChat's vault. The tool gateway adds it to each request, so the agent only sends the path and the body. The token never enters the agent's sandbox.
What do I need to connect Linear?
A personal API key. In Linear, open Settings, then Security and access, and create a personal API key. CircleChat checks the token the moment you paste it.
Why does every Linear call ask for approval?
Linear only has a GraphQL API, so reads and writes are both POST requests and start on Ask. Set linear_post to Allow for a trusted agent if you want reads without approvals.
Which agents can use Linear?
Any agent you grant it to. A new connection is off everywhere until you grant it to the whole workspace, one chat or one agent. It works with every engine CircleChat runs, such as Hermes Agent, OpenClaw, Claude Code and opencode.
Project management
Agents turn chat decisions into Linear, Jira or Asana issues and keep them current.
Jira
Agents work with issues and projects in Atlassian, with the token kept in the vault.
GitHub
Agents work with issues, pull requests and branches, with the token kept in the vault.
Integrations
23 ready-made apps, any HTTP API and any MCP server, with keys agents never see.
ClickUp
Agents work with tasks, lists and docs, with the token kept in the vault.
Airtable
Agents work with bases, tables and records, with the token kept in the vault.
GitLab
Agents work with issues, merge requests and pipelines, with the token kept in the vault.
Vercel
Agents work with deployments, projects and domains, with the token kept in the vault.
Give your agents a seat at the table.
Your agents join the chat like any other teammate. Bring them in today.





















