usemotion-mcp-server
Enables interaction with the Motion API for task and project management, including listing, creating, updating, and deleting tasks, projects, comments, and workspaces.
README
usemotion-mcp-server
MCP server for the Motion API, running on Bun. Supports two transports, selected with the MCP_TRANSPORT environment variable:
stdio(default) — local use; readsMOTION_API_KEYfrom the environmenthttp— streamable HTTP, deployable to Vercel; each client sends its own Motion API key as a request header (X-API-KeyorAuthorization: Bearer), which is forwarded to the Motion API for that request only. The server stores no credentials; requests without a key get a 401.
Setup
-
Create an API key in Motion (Settings → API).
-
For stdio mode, create a
.envfile in the project root:cp .env.example .env # then fill in MOTION_API_KEY -
Install dependencies:
bun install
Build
Compile a standalone binary (no Bun required at runtime):
bun run compile # produces bin/usemotion-mcp-server
The binary still auto-loads .env from the directory it runs in; otherwise set MOTION_API_KEY in its environment.
Usage
HTTP mode (local)
MCP_TRANSPORT=http bun run src/index.ts # serves http://localhost:3000/api/mcp (PORT to override)
Clients authenticate per request:
claude mcp add --transport http motion http://localhost:3000/api/mcp --header "X-API-Key: your-key-here"
Deploy to Vercel
api/mcp.ts + vercel.json ("bunVersion": "1.x") make the repo deployable as-is:
vercel deploy # then connect clients to https://<your-app>.vercel.app/api/mcp
Do not set MOTION_API_KEY on the deployment — keys come from client headers and are never stored.
stdio mode — Claude Code
claude mcp add motion -- bun run /path/to/usemotion-mcp-server/src/index.ts
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"motion": {
"command": "bun",
"args": ["run", "/path/to/usemotion-mcp-server/src/index.ts"],
"env": { "MOTION_API_KEY": "your-key-here" }
}
}
}
Note: Bun auto-loads .env from the working directory, so the env block is only needed if the server isn't started from the project root.
Tools
| Tool | Description |
|---|---|
list_tasks |
List tasks with filters (workspace, project, status, assignee, name, label) |
get_task |
Get a task by id |
create_task |
Create a task (supports auto-scheduling, priority, labels, markdown description) |
update_task |
Update a task |
delete_task |
Delete a task |
move_task |
Move a task to another workspace |
unassign_task |
Remove a task's assignee |
list_projects |
List projects in a workspace |
get_project |
Get a project by id |
create_project |
Create a project |
list_workspaces |
List workspaces |
list_users |
List users (find assignee ids) |
get_current_user |
Get the user tied to the API key |
list_statuses |
List task statuses in a workspace |
get_schedules |
Get schedules used by auto-scheduling |
list_comments |
List comments on a task |
create_comment |
Comment on a task |
Notes
- Motion's rate limit is 12 requests/minute on individual plans; the client retries 429s with backoff (honors
Retry-After). - List endpoints are cursor-paginated: pass
cursorfrom the previous response'smeta.nextCursor.
Development
bun run typecheck # tsc --noEmit
bun run scripts/smoke.ts # stdio smoke test: lists tools, then create → get → update → delete a task
bun run scripts/smoke-http.ts # HTTP smoke test: 401 without key, then list tools + workspaces via header auth
# (start the server first: MCP_TRANSPORT=http bun run src/index.ts)
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.