Basecamp

Implements a complete OAuth 2.0 flow using a Flask-based web interface (oauth_app.py) that handles token exchange, local storage with expiration detection, and automatic token refresh without user intervention. The system stores tokens locally and detects expiration via get_token() and store_token() functions, automatically refreshing credentials before API calls fail, eliminating manual re-authentication cycles.

Wraps the Basecamp 3 REST API as a standardized Model Context Protocol (MCP) server using Anthropic's FastMCP framework (basecamp_fastmcp.py), exposing 46 tools through async function decorators that handle protocol compliance, tool registration, and request/response marshaling. The FastMCP('basecamp') instance automatically converts Python function signatures into MCP tool schemas and manages bidirectional communication with AI clients like Claude Desktop and Cursor IDE.

Exposes get_projects() and get_project() tools that retrieve all accessible Basecamp projects or specific project details including metadata (name, description, status, members). The implementation enables AI agents to discover available projects and understand project structure before performing operations.

Implements a BasecampSearch class that executes search queries across all accessible Basecamp projects simultaneously, aggregating results from multiple API endpoints and deduplicating matches. The search_basecamp() and global_search() tools support both project-scoped and workspace-wide queries, with result optimization that filters and ranks matches across todos, documents, messages, and other content types.

Provides complete todo lifecycle management through get_todolists(), get_todos(), create_todo(), update_todo(), delete_todo(), complete_todo(), and uncomplete_todo() tools that map directly to Basecamp 3 API endpoints. The implementation handles todo state transitions (pending → completed → pending) and supports bulk operations, with each tool accepting structured parameters for title, description, due dates, and assignee information.

Exposes card table (Kanban board) functionality through get_card_table(), get_columns(), get_cards(), create_card(), update_card(), move_card(), create_column(), update_column(), and move_column() tools that manage board structure and card positioning. The implementation supports hierarchical card organization with card steps (sub-tasks) via get_card_steps() and create_card_step(), enabling multi-level task breakdown within a single card table.

Provides document access through get_documents() and related tools that retrieve document metadata, content, and file information from Basecamp projects. The implementation extracts structured metadata including creator, timestamps, and file references, enabling AI agents to index and analyze project documentation without manual file downloads.

Exposes team communication through get_campfire_lines() for chat messages and get_comments() for item-level comments, retrieving conversation history with metadata including creator, timestamp, and content. The implementation supports querying comments on any Basecamp item (todos, documents, cards) enabling AI agents to understand discussion context and decision rationale.

Provides access to Basecamp's check-in and questionnaire features through get_daily_check_ins() and get_question_answers() tools, retrieving structured responses with metadata. The implementation enables AI agents to aggregate team status updates and survey responses for reporting, trend analysis, and team health monitoring.

Provides automated configuration generation for different AI clients through generate_cursor_config.py and generate_claude_desktop_config.py, creating client-specific MCP server configuration files with proper paths, environment variables, and tool registration. The implementation handles client-specific requirements (Cursor vs Claude Desktop) and generates ready-to-use configuration without manual editing.

Implements BasecampClient class with built-in rate limiting, automatic retry logic, and error handling for Basecamp API interactions. The client manages HTTP session pooling, request/response logging, and graceful degradation when rate limits are exceeded, with exponential backoff for transient failures.