Skip to main content

Announcing StackOne Defender: leading open-source prompt injection guard for your agent Read More

Linear MCP Server
for AI Agents

Production-ready Linear MCP server with 84 extensible actions — plus built-in authentication, security, and optimized execution.

Linear logo
Linear MCP Server
Built by StackOne StackOne

Coverage

84 Agent Actions

Create, read, update, and delete across Linear — and extend your agent's capabilities with custom actions.

Authentication

Agent Tool Authentication

Per-user OAuth in one call. Your Linear MCP server gets session-scoped tokens with zero credentials stored on your infra.

Agent Auth →

Security

Agent Protection

Every Linear tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.

Prompt Injection Defense →

Performance

Max Agent Context. Min Cost.

Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Linear call.

Tools Discovery →

What is the Linear MCP Server?

A Linear MCP server lets AI agents read and write Linear data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Linear MCP server ships with 84 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Cursor, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.

All Linear MCP Tools and Actions

Every action from Linear's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.

Agent Sessions

  • List Agent Sessions

    Retrieve all agent sessions

  • Get Agent Session

    Retrieve a specific agent session by ID

Comments

  • Create Comment

    Create a new comment on an issue

  • List Comments

    Retrieve all comments with optional filtering by issue

  • Get Comment

    Retrieve a specific comment by ID

  • Update Comment

    Update an existing comment's body

  • Delete Comment

    Delete a comment by ID

Customers

  • List Customers

    Retrieve all customers with optional filtering

  • Get Customer

    Retrieve a specific customer by ID

Customer Needs

  • Create Customer Need

    Create a new customer need attached to an issue, project, or comment

  • List Customer Needs

    Retrieve all customer needs with optional filtering

  • Get Customer Need

    Retrieve a specific customer need by ID

  • Update Customer Need

    Update an existing customer need's body or customer association

  • Delete Customer Need

    Delete a customer need by ID

Customer Status

  • Create Customer Status

    Create a new customer status with name and optional description, color, and position

  • Get Customer Status

    Retrieve a specific customer status by ID

  • Update Customer Status

    Update an existing customer status's name, description, color, or position

  • Delete Customer Status

    Delete a customer status by ID

Customer Tiers

  • Create Customer Tier

    Create a new customer tier with name and optional description

  • List Customer Tiers

    Retrieve all customer tiers

  • Get Customer Tier

    Retrieve a specific customer tier by ID

  • Update Customer Tier

    Update an existing customer tier's name or description

  • Delete Customer Tier

    Delete a customer tier by ID

Cycles

  • Create Cycle

    Create a new cycle for a team

  • List Cycles

    Retrieve all cycles with optional filtering by team

  • Get Cycle

    Retrieve a specific cycle by ID

  • Update Cycle

    Update an existing cycle's name, description, or dates

Documents

  • List Documents

    Retrieve all documents with optional filtering

  • Get Document

    Retrieve a specific document by ID

External Users

  • List External Users

    Retrieve all external users for the organization

  • Get External User

    Retrieve a specific external user by ID

Initiatives

  • Create Initiative

    Create a new initiative to group projects

  • List Initiatives

    Retrieve all initiatives with optional filtering

  • Get Initiative

    Retrieve a specific initiative by ID

  • Update Initiative

    Update an existing initiative's name, description, dates, or other properties

  • Delete Initiative

    Delete an initiative by ID

Issues

  • Create Issue

    Create a new issue in Linear with title, description, team, and optional fields

  • List Issues

    Retrieve all issues with optional filtering by team, project, assignee, or status

  • Get Issue

    Retrieve a specific issue by ID or identifier

  • Search Issues

    Search issues by text term with optional filtering and pagination

  • Update Issue

    Update an existing issue's title, description, assignee, priority, state, or other fields

  • Delete Issue

    Delete an issue by ID

Issue Labels

  • Create Issue Label

    Create a new issue label for a team

  • List Issue Labels

    Retrieve all issue labels with optional filtering by team

  • Get Issue Label

    Retrieve a specific issue label by ID

  • Update Issue Label

    Update an existing issue label's name, description, or color

  • Delete Issue Label

    Delete an issue label by ID

Projects

  • Create Project

    Create a new project with name, description, and optional team associations

  • List Projects

    Retrieve all projects in the workspace with optional filtering

  • Get Project

    Retrieve a specific project by ID with full details

  • Update Project

    Update an existing project's details

  • Delete Project

    Delete a project by ID

Project Labels

  • Create Project Label

    Create a new project label

  • List Project Labels

    Retrieve all project labels with optional filtering

  • Get Project Label

    Retrieve a specific project label by ID

  • Update Project Label

    Update an existing project label's name, description, or color

  • Delete Project Label

    Delete a project label by ID

Project Milestones

  • Create Project Milestone

    Create a new milestone for a project

  • List Project Milestones

    Retrieve all milestones for a project

  • Get Project Milestone

    Retrieve a specific project milestone by ID

  • Update Project Milestone

    Update an existing project milestone's name, description, or target date

  • Delete Project Milestone

    Delete a project milestone by ID

Project Status

  • Create Project Status

    Create a new project status with name, type, and optional description, color, and position

  • Get Project Status

    Retrieve a specific project status by ID

  • Update Project Status

    Update an existing project status's name, description, type, color, or position

Teams

  • List Teams

    Retrieve all teams in the workspace

  • Get Team

    Retrieve a specific team by ID

  • Update Team

    Update an existing team's name, description, icon, color, or other properties

Users

  • List Users

    Retrieve all users in the workspace, use the filter input to search.

  • Get User

    Retrieve a specific user by ID

  • Update User

    Update an existing user's profile information

Webhooks

  • Create Webhook

    Create a new webhook to receive HTTP notifications for data updates

  • List Webhooks

    Retrieve all webhooks in the organization

  • Get Webhook

    Retrieve a specific webhook by ID

  • Update Webhook

    Update an existing webhook's URL, enabled status, or resource types

  • Delete Webhook

    Delete a webhook by ID

Workflow States

  • List Workflow States

    Retrieve all workflow states with optional filtering by team

  • Get Workflow State

    Retrieve a specific workflow state by ID

Other

  • Get Application Info

    Get basic information for an application by client ID

  • List Customer Statuses

    Retrieve all customer statuses

  • List Project Statuses

    Retrieve all project statuses

  • Archive Cycle

    Archive a cycle by ID

  • Issue Filter Suggestion

    Suggests filters for an issue view based on a text prompt

  • Archive Project Status

    Archive a project status by ID

Set Up Your Linear MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to Linear in under 10 lines of code.

MCP Clients

Agent Frameworks

Claude Desktop
{
  "mcpServers": {
    "stackone": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://api.stackone.com/mcp?x-account-id=<account_id>",
        "--header",
        "Authorization: Basic <YOUR_BASE64_TOKEN>"
      ]
    }
  }
}

More Project Management MCP Servers

Azure DevOps

172+ actions

Bitbucket

134+ actions

Jira

134+ actions

Confluence

133+ actions

Trello

133+ actions

Asana

126+ actions

GitLab

125+ actions

Linear MCP Server FAQ

Linear MCP server vs direct API integration — what's the difference?
A Linear MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Linear. A Linear MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Linear at runtime. StackOne provides both.
How does Linear authentication work for AI agents?
Linear authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Linear account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.
Are Linear MCP tools vulnerable to prompt injection?
Yes — Linear MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Linear agent and how do I avoid it?
Context bloat happens when Linear tool schemas and API responses eat your Linear agent's memory, preventing it from reasoning effectively. A single Linear query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Linear agent can access?
Yes — you can limit which actions your Linear agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Linear MCP server?
Yes — you can create custom agent actions for your Linear MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Linear's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Linear MCP server?
Skip a Linear MCP server if your integration is purely software-to-software — direct Linear API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Linear actions at runtime.
What AI frameworks and AI clients does the StackOne Linear MCP server support?
The StackOne Linear MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.

Put your AI agents to work

All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.