Linear MCP Server

Linear's MCP server connects AI agents to Linear issue tracking systems, enabling automated task creation, cycle tracking, project roadmap updates, and triage workflows. It allows agents to parse incoming requests into organized engineering issues, update project statuses, and link issues with Git pull requests.

Start for free

Linear MCP Server

Benefits with Ory + Linear MCP Server

Linear's MCP server lets your agents search, create, and update issues, projects, comments, and cycles in your Linear workspace. Triage automation saves time, while a misfiring agent can flood a backlog or close the wrong work. Ory Agent Security lets planning agents read issues while creation and updates stay with the triage agents you approve, and every change is attributed to the user behind it.

View documentation

Use Cases

— 01 use case

Agent IAM

Summarizers read at Read, triage agents file and comment at Write, merges and deletions are Admin only, and Block keeps other agents out of Linear.

Explore Agent IAM

Core Functionality

— 04 capabilities

Read, write, admin, or no access
Ory Agent Security classifies every tool on the Linear MCP server as read, write, or admin, so you can give each user, team, or agent type only the level it needs: read for planning agents, write for triage agents, admin for the few agents trusted to remove or share work, and no access for agents with no role in product work.
Enforced before execution
Ory Agent Security checks each tool call against the user, the agent acting for them, and any sub-agent inside the agent harness, so a denied issue deletion stops before it reaches Linear, with nothing to roll back and no gateway to deploy.
Observe, then enforce
Observe mode shows which agents create or change issues and for whom without blocking anything, so you can apply Ory's pre-built policy for the Linear MCP server and enforce it on your own schedule.
Complete audit trail
Every allow and deny decision on the Linear MCP server streams to your SIEM through OpenTelemetry with the user, agent, and action attached, so you can show which agent closed or edited an issue and on whose behalf.