Provides tools for managing Basecamp projects, including retrieving project details, messages, todos, and schedules, as well as creating messages and updating todo completion status.
Basecamp MCP Server
Connect your Basecamp workspace to Claude and other AI tools via the Model Context Protocol.
Setup
1. Get Basecamp API Credentials
Go to Basecamp and log in
Click your profile → "Settings" → "Personal access tokens" (or "Integrations & apps" → "API credentials")
Create a new token (it needs "all access")
Copy the token
Find your Account ID in the URL when you're in your workspace (e.g.,
https://3.basecamp.com/ACCOUNT_ID
)
2. Set Environment Variables
Or create a .env
file in the project root (add to .gitignore
):
3. Install Dependencies
4. Run the Server
Or run it directly:
Features
Tools (Functions Claude Can Call)
get_projects
- List all Basecamp projectsget_project_details
- Get detailed info about a projectget_messages
- Get recent messages from a projectget_message_with_comments
- Get a specific message with all commentsget_todos
- Get todo items (with optional filtering by completion)create_message
- Create a new message in a projectupdate_todo
- Mark a todo as complete/incompleteget_schedules
- Get schedules from a projectclear_cache
- Clear all cached dataget_cache_stats
- View cache statistics
Resources (Data Claude Can Read)
basecamp://projects
- List of all projectsbasecamp://project/{project_id}/summary
- Project summary with recent activity
Caching
The server uses SQLite for persistent caching with TTL (Time To Live):
Projects: 5 minutes cache
Messages: 2 minutes cache
Todos: 2 minutes cache
Project details: 10 minutes cache
Use get_cache_stats
to see cache hit rates and size, or clear_cache
to force fresh data.
Project Structure
Integration with Claude Desktop
To use with Claude Desktop:
Edit
~/Library/Application Support/Claude/claude_desktop_config.json
(macOS) or the Windows equivalentAdd the server:
Restart Claude Desktop
Development
Testing the Server
Viewing Cache
The cache database is stored in basecamp_cache.db
in your working directory. You can inspect it with:
API Reference
Basecamp API v1 Endpoints Used
GET /projects.json
- List projectsGET /projects/{id}.json
- Get project detailsGET /projects/{id}/messages.json
- List messagesGET /projects/{id}/messages/{message_id}.json
- Get messageGET /projects/{id}/messages/{message_id}/comments.json
- Get commentsGET /projects/{id}/todos.json
- List todosGET /projects/{id}/todolists/{list_id}/todos.json
- Get todos from listPUT /projects/{id}/todos/{todo_id}.json
- Update todoPOST /projects/{id}/messages.json
- Create messageGET /projects/{id}/schedules.json
- List schedules
License
MIT
This server cannot be installed
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
Connects Basecamp workspaces to AI tools, enabling management of projects, messages, todos, and schedules through natural language interactions. Features persistent caching and supports both reading workspace data and performing actions like creating messages and updating todos.