Connect Linear MCP to your AI agents, securely.
One secured endpoint for every Linear call your AI agents make, scoped per user, inspected, and logged.Try Linear MCP now
What your agents can ask once Linear MCP is connected.
“List the issues assigned to me”
“Create an issue for this bug in the platform team”
“What is in the current cycle?”
“Move this issue to In Review”
“Show me the projects due this quarter”
“Add a comment on that issue with the findings”
Select the tools your AI agents can call
78 tools from the Linear MCP schema.
Showing 78 tools
What Linear MCP exposes
Linear MCP groups its 78 tools into 12 categories, each with a suggested starting policy.
| Category | Covers | Access | Suggested policy |
|---|---|---|---|
| Issues | Issue retrieval, creation, updates, statuses, labels, attachments, templates and sharing | Read / Write | Audit changes |
| Comments | Comments on issues, projects, initiatives, documents, milestones and status updates | Read / Write | Audit publishing |
| Cycles | Cycles for a team | Read | Allow cycle lookups |
| Documents | Workspace documents: read, create and update | Read / Write | Review content before publishing |
| Projects | Projects, project details, creation, updates, labels, milestones and status updates | Read / Write | Scope projects; audit changes |
| Teams | Teams in the workspace and their details | Read | Limit organization access |
| Users | Workspace users and their details, and inbox notifications | Read / Write | Limit organization access |
| Documentation | Search across Linear's own documentation | Read | Allow documentation searches |
| Initiatives | Initiatives, initiative labels and their retirement or restoration | Read / Write | Audit initiative changes; they roll up many projects |
| Customers | Customers and customer needs: listing, creation, updates and deletion | Read / Write | Treat customer data as sensitive; require approval for deletes |
| Code Review | Linear diffs (pull requests), review threads, diff comments, reviews and merges | Read / Write | Require approval before merging diffs or submitting reviews |
| Releases | Releases, release pipelines and release notes | Read / Write | Review release notes before publishing |
Connect Linear MCP to your AI agent
Four steps, under ten minutes.
- 01
Sign in to NeuralTrust
Open the NeuralTrust platform, sign in and go to Getting started, then Connect your tools.
- 02
Choose your agent
When asked which agent you use, pick Claude Code, Codex, Cursor, Windsurf, Copilot or your own code.
- 03
Connect Linear
Find Linear in the tool list and connect it.
- 04
Connect your agent
Follow the steps on screen to add the config to your agent, then send the test prompt.
Permissions down to the single tool
You do not allow Linear MCP or block it. You allow the exact tools each agent can call, one by one.
| Linear MCP | 78 TOOLS AVAILABLE |
|---|---|
| Code review agent | 4 tools, read only |
| Issue triage bot | 9 tools |
| Platform team assistant | all 78 tools |
- Tool by toolConnecting the server is not the unit of access. Each tool is granted on its own.
- Default denyA tool you have not enabled is never exposed to the agent.
- Approval on writesTools that change or delete things can require a human to confirm.
Is Linear MCP secure?
One endpoint instead of raw credentials. Every call is checked against policy and logged.
| AI agentsConnect through your MCP client configuration. | NeuralTrustApply controls based on your configuration. | Linear MCP78 documented tools. |
|---|---|---|
| Coding assistants | Connection & credentialsper user | Issues20 tools |
| Internal copilots | Tool access policiesdeny by default | Projects13 tools |
| Workflow automations | Request & response inspectioninline | Initiatives8 tools |
| Compatible MCP clients | Activity monitoringalerts and logs | All other tools37 tools |
Use Linear MCP with any AI agent framework
Setup guides for the tools your team already uses.
- Claude CodeSetup guide
- CursorSetup guide
- CodexSetup guide
- WindsurfSetup guide
- Gemini CLISetup guide
- Google AntigravitySetup guide
- GitHub CopilotSetup guide
- Claude EnterpriseSetup guide
- Microsoft Copilot StudioSetup guide
- Open WebUISetup guide
- LangChainSetup guide
- HaystackSetup guide
- Strands AgentsSetup guide
- Vercel AI SDKSetup guide
- n8nSetup guide
Common questions about running Linear MCP through TrustGate.
Other MCP servers
More servers from the catalog.
GitHub
Securely connect your AI agents to GitHub through TrustGate: repositories, issues, pull requests, Actions, and 92 more tools, scoped per agent and logged.
96 toolsViewNotion
Securely connect your AI agents to Notion through TrustGate: pages, databases, comments, files and agent sessions, scoped per agent and logged.
65 toolsViewSalesforce
Securely connect your AI agents to Salesforce through TrustGate: SOQL queries, cross-object search, and record create, update and delete, scoped per agent and logged.
11 toolsView
Connect Linear MCP instantly
Pick the tools, point your agent at TrustGate, and Linear MCP is live: scoped, inspected, logged.