sub-agents-mcp and mcp
About sub-agents-mcp
shinpr/sub-agents-mcp
Define task-specific AI sub-agents in Markdown for any MCP-compatible tool.
Markdown-defined agents execute via pluggable CLI backends (Cursor, Claude Code, Gemini, or Codex), with built-in session management and error handling for multi-step workflows. The MCP server architecture enables teams to define reusable agents once and consume them across any MCP-compatible IDE or tool, creating portable Claude Code–style sub-agent capabilities outside Claude's environment.
About mcp
mondaycom/mcp
Enable AI agents to work reliably - giving them secure access to structured data, tools to take action, and the context needed to make smart decisions.
Implements the Model Context Protocol (MCP) as a standardized interface for AI agents to query monday.com's work OS via GraphQL API, with both hosted and self-hosted deployment options. Provides TypeScript-based server and agent toolkit packages compatible with Claude, ChatGPT, Cursor, and other AI platforms, handling OAuth authentication and workspace-level access controls. Supports real-time board management, task tracking, and workflow automation without requiring agents to understand monday.com's API directly.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work