basecamp-mcp
Basic BaseCamp MCP server
Documentation
Basecamp MCP Server
Connect your Basecamp workspace to Claude and other AI tools via the Model Context Protocol.
Setup
1. Get Basecamp API Credentials
1. Go to Basecamp and log in
2. Click your profile → "Settings" → "Personal access tokens" (or "Integrations & apps" → "API credentials")
3. Create a new token (it needs "all access")
4. Copy the token
5. 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
export BASECAMP_API_TOKEN="your_token_here"
export BASECAMP_ACCOUNT_ID="your_account_id_here"Or create a `.env` file in the project root (add to `.gitignore`):
BASECAMP_API_TOKEN=your_token_here
BASECAMP_ACCOUNT_ID=your_account_id_here3. Install Dependencies
uv sync4. Run the Server
uv run python -m basecamp_mcp.serverOr run it directly:
uv run python src/basecamp_mcp/server.pyFeatures
Tools (Functions Claude Can Call)
- `get_projects` - List all Basecamp projects
- `get_project_details` - Get detailed info about a project
- `get_messages` - Get recent messages from a project
- `get_message_with_comments` - Get a specific message with all comments
- `get_todos` - Get todo items (with optional filtering by completion)
- `create_message` - Create a new message in a project
- `update_todo` - Mark a todo as complete/incomplete
- `get_schedules` - Get schedules from a project
- `clear_cache` - Clear all cached data
- `get_cache_stats` - View cache statistics
Resources (Data Claude Can Read)
- `basecamp://projects` - List of all projects
- `basecamp://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
BaseCampMCP/
├── src/
│ └── basecamp_mcp/
│ ├── __init__.py
│ ├── server.py # Main MCP server with tools & resources
│ └── cache.py # SQLite cache manager
├── pyproject.toml # Project configuration
└── README.mdIntegration with Claude Desktop
To use with Claude Desktop:
1. Edit `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS) or the Windows equivalent
2. Add the server:
{
"mcpServers": {
"basecamp": {
"command": "uv",
"args": ["run", "--with", "mcp", "python", "-m", "basecamp_mcp.server"],
"cwd": "/Users/kaustubh/Documents/BaseCampMCP"
}
}
}3. Restart Claude Desktop
Development
Testing the Server
# Run with verbose logging
uv run python -m basecamp_mcp.serverViewing Cache
The cache database is stored in `basecamp_cache.db` in your working directory. You can inspect it with:
sqlite3 basecamp_cache.db
sqlite> SELECT key, hits, expires_at FROM cache ORDER BY hits DESC;API Reference
Basecamp API v1 Endpoints Used
- `GET /projects.json` - List projects
- `GET /projects/{id}.json` - Get project details
- `GET /projects/{id}/messages.json` - List messages
- `GET /projects/{id}/messages/{message_id}.json` - Get message
- `GET /projects/{id}/messages/{message_id}/comments.json` - Get comments
- `GET /projects/{id}/todos.json` - List todos
- `GET /projects/{id}/todolists/{list_id}/todos.json` - Get todos from list
- `PUT /projects/{id}/todos/{todo_id}.json` - Update todo
- `POST /projects/{id}/messages.json` - Create message
- `GET /projects/{id}/schedules.json` - List schedules
License
MIT
Frequently asked questions
What is basecamp-mcp?
basecamp-mcp is Basic BaseCamp MCP server
How do I install basecamp-mcp?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is basecamp-mcp open source?
Yes — it is hosted on GitHub at https://github.com/kbhalerao/basecamp-mcp.
Related MCP tools
Damn Vulnerable MCP Server Python-based implementation. Trusted by 1200+ developers. Trusted by 1200+ developers. Trusted by 1200+ developers.
A Model Context Protocol (MCP) server that enables secure interaction with MySQL databases Python-based implementation. Trusted by 900+ developers.
Query MCP enables end-to-end management of Supabase via chat interface: read & write query executions, management API support, automatic migration versioning...
Model Context Protocol with Neo4j Python-based implementation. Trusted by 700+ developers. Trusted by 700+ developers. Trusted by 700+ developers.
An MCP server that provides control over Android devices via adb Python-based implementation. Trusted by 500+ developers.
A Model Context Protocol (MCP) server for PostgreSQL databases with enhanced capabilities for AI agents. Python-based implementation.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP