claude-code-mcp and activitypub-mcp

These two projects appear to be competing implementations of an MCP (Model Context Protocol) server for connecting LLMs like Claude to external systems, with project B specifically targeting the Fediverse.

claude-code-mcp
57
Established
activitypub-mcp
50
Established
Maintenance 10/25
Adoption 7/25
Maturity 25/25
Community 15/25
Maintenance 10/25
Adoption 5/25
Maturity 24/25
Community 11/25
Stars: 34
Forks: 6
Downloads:
Commits (30d): 0
Language: JavaScript
License: MIT
Stars: 12
Forks: 2
Downloads:
Commits (30d): 0
Language: TypeScript
License: MIT
No risk flags
No risk flags

About claude-code-mcp

KunihiroS/claude-code-mcp

MCP Server connects with claude code local command.

Exposes Claude Code CLI capabilities (explain, review, fix, edit, test code) as MCP tools through stdio-based JSON communication, using Base64 encoding to safely handle special characters in natural language inputs. Implements request routing via `child_process.spawn` to execute templated or custom Claude CLI commands and return results to MCP hosts. Integrates with Claude Desktop and other MCP hosts, supporting Node.js 18+ with configurable logging and environment-based CLI path configuration.

About activitypub-mcp

cameronrye/activitypub-mcp

A comprehensive Model Context Protocol (MCP) server that enables LLMs like Claude to explore and interact with the existing Fediverse through standardized MCP tools, resources, and prompts.

Implements 53 MCP tools spanning discovery, authenticated posting/interactions, and data export across ActivityPub-compatible servers (Mastodon, Pleroma, Misskey), with dual stdio/HTTP transport modes and multi-account credential management. Built in TypeScript with high-performance caching, built-in audit logging, rate limiting, and instance blocklists for secure LLM-driven fediverse operations. The architecture enables direct ActivityPub protocol interaction through WebFinger discovery and standardized MCP resources for timeline, trending, and instance information access.

Scores updated daily from GitHub, PyPI, and npm data. How scores work