Provides tools for searching, reading, creating, updating, and commenting on Linear issues and projects, with a local cache to reduce API usage.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Linear Cache MCP list my open issues"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A cache-first MCP server for Linear that lets coding agents read from a local JSON cache instead of burning through API request budgets on every query.
13 MCP tools — search, read, create, update, and comment on Linear issues and projects
Local JSON cache — fast planning reads with zero API cost
Request budget tracking — prevents accidentally blowing through Linear's API rate limits
Write-through safety — live-fetches entities before mutating, patches cache after writes
Project-first model — issues live inside projects; projects hold durable context
Related MCP server: mcp-server-linear
Linear's API has rate limits. Coding agents that query Linear directly for every context read can exhaust them quickly. This server maintains a local mirror of your team's issues and projects, serves reads from cache when fresh, and only hits the Linear API for writes or when the cache is stale.
npx linear-cache-mcpOr for development:
cd packages/linear-cache-mcp
npm install
cp .env.example .env # add your LINEAR_API_KEY
npm test
npm startFull setup instructions are in the package README, including Pi coding agent integration.
Path | Purpose |
| MCP server |
| Agent skill template for Linear workflows |
| Ready-to-copy configs for Pi projects |
| Generic MCP client config template |
npm: linear-cache-mcp
Linear: linear.app
Pi: pi-coding-agent
MIT
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP server for interacting with the Supabase platform
MCP (Model Context Protocol) server for Appwrite
AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ch-raph/linear-cache-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server