Linear MCP server
Arc0’s Linear tools focus on two tasks: reading a team’s issues and creating new ones. Use them to review a backlog and turn a concrete request into tracked work. Connect through Arc0 to use the actions your identity is allowed to call.
Working with Linear
Use linear.list_issues when a question concerns work already tracked by one Linear team. Supply that team’s UUID, which can be copied from Linear, and follow the returned cursor for additional pages. A page contains at most 50 issues; make the coverage clear when presenting a backlog summary or deciding whether a request is already represented.
When new work is needed, draft a title and description with the expected result and any relevant reproduction details. linear.create_issue files it in the chosen team. This works for a bug found during implementation, a documentation follow-up, or a small task agreed during a review. The team selection is explicit rather than inferred from an ambiguous project name.
The current action set stays narrow. It does not edit existing issues, add comments, or search across teams. If an issue creation loses its response, use linear.list_issues to inspect the team’s recent work before submitting again. A repeated create is another request and can leave duplicate issues for someone to clean up.
Official MCP reference: Linear documentation.
Agent workflows for Linear.
Review a team backlog
Use linear.list_issues with a known team UUID and continue through returned pages before summarizing coverage.
File a reproducible bug
Use linear.create_issue to record the observed behavior and reproduction steps in the selected team.
Capture a follow-up task
Use linear.create_issue for a specific next step agreed during a review, with enough context for its owner.
Check an uncertain submission
Use linear.list_issues to look for a recently submitted issue before deciding whether another creation is needed.
2 Linear actions, graded by risk.
These actions come from the Arc0 registry. Your identity, provider permissions and Arc0 policies determine which actions can run.
read
1Look things up, subject to your permissions.
- linear.list_issuesList issues
List issues in one Linear team (team UUID from Linear: Cmd/Ctrl+K, Copy model UUID), up to 50 per page. Use when the user asks what issues a team has. Not for comments or cross-team search. To continue, pass nextCursor as after.
write
1Create and change things. Allow, or ask the user first.
- linear.create_issueCreate issue
Create one issue in a Linear team. Use when the user asks to file, log or track new work in Linear. Not for comments, edits or bulk imports. A timed-out create may have succeeded: list the team's issues before trying again.
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Control access to Linear.
Connect the intended Linear account, authorize your AI client and set policies for its tools.
Provider permissions and Arc0 policy both apply. Allow reads, require approval for selected writes, or deny destructive actions. The audit log records execution decisions.
Configure policies and approvalsExample policy choices
- Read actions: allow where authorized
- linear.create_issue: require approval
Arc0 MCP endpoint: https://api.arc0.ai/mcp
How Linear connects.
Connect Linear using OAuth. OAuth grants the provider scopes shown during consent; API keys and other credentials retain the permissions configured at the provider. Arc0 stores credentials in its encrypted vault and does not pass them to the model. Disconnect to remove access through Arc0; revoke a key at the provider to invalidate it there. Token refresh and provider-side revocation depend on the authentication lane and provider.
The connection serves authorized calls through Arc0 MCP and REST. How Arc0 handles credentials →
- AUTH
- OAuth
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Linear with your AI client.
Sign in to Arc0 and connect Linear in My apps. Then authorize your AI client separately. It only receives tools and accounts allowed for that identity.
Linear with Claude
Claude Desktop + Claude Code
- In Claude Desktop, add Arc0 through the remote MCP settings and use OAuth. Follow the generic remote-client steps if your account’s interface differs.
- For Claude Code, run the command below. Open /mcp, select Arc0, and authenticate in your browser. Select your workspace and review access.
- Check the connection with claude mcp get arc0.
claude mcp add --transport http --scope user arc0 https://api.arc0.ai/mcpFull MCP setup and troubleshootingLinear with ChatGPT
ChatGPT on the web
- Open Plugins in ChatGPT, select the plus button, then Add custom MCP server.
- Name it Arc0, enter the server URL below, and choose OAuth. Use dynamic client registration if asked; no Arc0 API key is needed.
- Review the notice and select Create as a plugin. Complete Arc0 sign-in, workspace selection and consent, then install and select the plugin in your conversation. Labels and access vary by account; managed workspaces may require administrator approval.
https://api.arc0.ai/mcpFull MCP setup and troubleshootingLinear with OpenAI Codex
Codex app + CLI
- Run the registration command below. The app and CLI share ~/.codex/config.toml.
- Complete browser OAuth, choose your Arc0 workspace, and review access. If authentication does not start, run codex mcp login arc0.
- Check codex mcp list, then open a new Codex chat. Inspect an existing arc0 entry before changing it.
codex mcp add arc0 --url https://api.arc0.ai/mcpFull MCP setup and troubleshootingLinear with Cursor
Remote MCP setup
- Add Arc0 in your client’s remote MCP settings using the server URL below.
- Choose OAuth, sign in to Arc0, select the intended workspace and review access.
- Confirm the server is connected and start with an allowed read. These are generic remote-MCP steps; consult your client’s settings for its current interface.
https://api.arc0.ai/mcpFull MCP setup and troubleshootingLinear with VS Code
Remote MCP setup
- Add a remote HTTP MCP server named Arc0 using the URL below.
- Use OAuth and finish Arc0 sign-in, workspace selection and consent.
- Confirm discovery succeeds before requesting a read. These are generic remote-MCP steps; client UI and availability may differ.
https://api.arc0.ai/mcpFull MCP setup and troubleshootingLinear with Any MCP client
Streamable HTTP
- Use a client that supports remote MCP over Streamable HTTP. Add the server URL below and choose OAuth.
- For a client without OAuth, use a self-bound API key with execute permission in the X-API-Key header. Store it in secret storage or an environment variable, outside source control. Never send both an API key and an OAuth bearer token.
- Use the MCP clients guide for the SDK transport example and Embedded identity for business-managed end users.
https://api.arc0.ai/mcpFull MCP setup and troubleshootingAfter setup, ask your agent to find an allowed read action, load its schema, and execute it on the intended account. Check Activity for the receipt. A connected MCP client alone does not confirm a successful provider call.
More project management apps.
Linear and Arc0, answered.
Is there an official Linear MCP server, and how does Arc0 differ?
Yes. Linear maintains an MCP server. Arc0 currently exposes just team issue listing and issue creation, with shared Arc0 connection management, policies, and audit logging.
Which permissions does Arc0 need for Linear?
OAuth requests read and issues:create and acts as the authorizing user. It does not request a general write grant. Team UUIDs are supplied to actions; Arc0 does not add a team-discovery action in this version.
Does this work with Claude, ChatGPT, Codex and Cursor?
Yes, through Arc0 MCP when your Claude, ChatGPT, Codex, or Cursor client supports remote MCP and your account permits it. Connect the app in Arc0 and configure your client using the Arc0 setup guide. App permissions still apply.
How are credentials stored, refreshed and revoked?
Credentials are encrypted in Arc0’s vault. Arc0 stores OAuth credentials, refreshes expiring access tokens, and retains replacement refresh tokens. Disconnect attempts token revocation. You can also remove the authorization in Linear; a failed remote cleanup should be checked there.
What happens with rate limits or errors?
Linear applies request and query-complexity limits. Arc0 surfaces API and authorization errors, including GraphQL failures, instead of presenting them as an empty backlog. Check the team’s issues before repeating a timed-out creation.
What is the availability of these Linear tools?
These tools are available. Connect the app in Arc0 and authorize your AI client. The action list describes the current implementation.
Plug Linear into your agent.
Linear MCP server: 2 actions including list issues, create issue. Connect through Arc0.
Free to build · MCP + REST · Audit log on every plan
Linear and its logo are trademarks of their respective owners. Arc0 is not affiliated with or endorsed by Linear.