Basecamp MCP Server
Provides tools for managing Basecamp projects, including retrieving project details, messages, todos, and schedules, as well as creating messages and updating todo completion status.
Click on "Deploy 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., "@Basecamp MCP Server show me my incomplete todos for the website redesign project"
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.
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
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.pyRelated MCP server: Basecamp MCP Server
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
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:
Edit
~/Library/Application Support/Claude/claude_desktop_config.json(macOS) or the Windows equivalentAdd the server:
{
"mcpServers": {
"basecamp": {
"command": "uv",
"args": ["run", "--with", "mcp", "python", "-m", "basecamp_mcp.server"],
"cwd": "/Users/kaustubh/Documents/BaseCampMCP"
}
}
}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 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
Available Tools
10 toolsclear_cacheB
Clear all cached data. Useful for debugging or forcing fresh data.
Inputs: no named parameters.
create_messageC
Create a new message in a project. Clears message cache for this project.
Inputs: project_id (required), subject (required), content (required).
get_cache_statsC
Get statistics about the cache.
Inputs: no named parameters.
get_messagesB
Get recent messages from a project. Results cached for 2 minutes.
Inputs: project_id (required), limit. Returns: result
get_message_with_commentsC
Get a specific message with all comments.
Inputs: project_id (required), message_id (required).
get_project_detailsC
Get detailed information about a specific project.
Inputs: project_id (required).
get_projectsA
List all Basecamp projects. Results are cached for 5 minutes.
Inputs: no named parameters. Returns: result
get_schedulesC
Get schedules from a project.
Inputs: project_id (required). Returns: result
get_todosC
Get todo items from a project or specific todo list. Optionally filter by completion status.
Inputs: project_id (required), list_id, completed. Returns: result
update_todoB
Update a todo item's completion status. Clears todo cache for this project.
Inputs: project_id (required), todo_id (required), completed (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 10 tools
Most tools have distinct purposes targeting different resources like messages, projects, todos, and cache. However, get_messages and get_message_with_comments could be slightly confusing as both retrieve messages, though the latter includes comments. Overall, the overlap is minimal and descriptions clarify the differences.
All tool names follow a consistent verb_noun pattern using snake_case, such as clear_cache, create_message, and get_projects. This uniformity makes the set predictable and easy for an agent to parse and understand.
With 10 tools, the server is well-scoped for Basecamp operations, covering key areas like projects, messages, todos, and cache management. Each tool serves a clear purpose without feeling excessive or insufficient for the domain.
The toolset provides good coverage for reading and updating Basecamp data, including CRUD-like operations for messages and todos, and project/schedule retrieval. A minor gap exists in creating or updating projects, schedules, or comments, but core workflows are supported.
Maintenance
Related MCP Connectors
Manage Redbooth tasks, task lists, comments, tags and files from Claude and other AI assistants.
Governed memory and workspace for any AI: tasks, calendar, mail and pages, with per-action consent.
Your Aurentia workspace — projects, CRM, tasks, deliverables — in Claude, Cursor or any MCP client.
Connect AI tools to Trilo workspaces — manage tasks, messages, pages, calendars, meetings, and more.
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables seamless integration with Basecamp 3 through 46 comprehensive API tools, allowing users to manage projects, todos, card tables, documents, campfire messages, and other Basecamp features through natural language interactions in Claude Desktop and Cursor IDE.335MIT
- AlicenseBqualityDmaintenanceEnables AI assistants to interact with Basecamp projects through natural language commands. Supports managing projects, to-do lists, messages, and creating tasks with full content rendering capabilities.6ISC
- AlicenseAqualityBmaintenanceEnables LLMs to interact with Basecamp projects, managing messages, todos, comments, people, and kanban boards through natural language. Supports comprehensive Basecamp operations including creating, reading, updating content with flexible output formats and URL parsing capabilities.5775 npm2MIT
- AlicenseBqualityDmaintenanceConnects AI assistants to the Basecamp 2 API, enabling management of projects, todos, messages, and people directly through natural language.1726 npmMIT