Tiger Linear MCP Server
# Tiger Linear MCP Server
A wrapper around the [Linear](https://linear.app/) API to provide some focused tools to LLMs via the [Model Context Protocol](https://modelcontextprotocol.io/introduction).
## Development
Cloning and running the server locally.
```bash
git clone git@github.com:timescale/tiger-linear-mcp-server.git
```
### Building
Run `npm i` to install dependencies and build the project. Use `npm run watch` to rebuild on changes.
Create a `.env` file based on the `.env.sample` file.
```bash
cp .env.sample .env
```
### Testing
The MCP Inspector is a very handy to exercise the MCP server from a web-based UI.
```bash
npx @modelcontextprotocol/inspector
```
| Field | Value |
| -------------- | --------------- |
| Transport Type | `STDIO` |
| Command | `node` |
| Arguments | `dist/index.js` |
#### Testing in Claude Desktop
Create/edit the file `~/Library/Application Support/Claude/claude_desktop_config.json` to add an entry like the following, making sure to use the absolute path to your local `tiger-linear-mcp-server` project, and use a valid api token.
```json
{
"mcpServers": {
"tiger-linear": {
"command": "node",
"args": [
"/absolute/path/to/tiger-linear-mcp-server/dist/index.js",
"stdio"
],
"env": {
"LINEAR_API_KEY": "lin_api_..."
}
}
}
}
```
TDQS
Scored across 4 tools
Each tool targets a distinct resource and granularity: single issue, list of issues, all users, and all projects. There is no overlap or ambiguity between singular and plural forms.
All tools follow the consistent 'get_<resource>' pattern, making the API intuitive and predictable. No mixed conventions or vague verbs.
Four tools is well within the ideal 3-15 range and each tool earns its place by covering the core read operations for issues, users, and projects. The count feels appropriate for a focused read-only server.
The tool surface is read-only only, with no create, update, or delete operations for issues or other resources. For a Linear server, there are also missing common resources like teams and cycles, leaving significant gaps for any agent needing to manage workflows.