graphlit-mcp-server and activitypub-mcp

These two projects are ecosystem siblings, as both are distinct implementations of the Model Context Protocol (MCP) server, with one (Graphlit) focused on the Graphlit platform and the other (activitypub-mcp) enabling LLMs to interact with the Fediverse using the same standardized protocol.

graphlit-mcp-server
64
Established
activitypub-mcp
50
Established
Maintenance 10/25
Adoption 10/25
Maturity 25/25
Community 19/25
Maintenance 10/25
Adoption 5/25
Maturity 24/25
Community 11/25
Stars: 372
Forks: 52
Downloads:
Commits (30d): 0
Language: TypeScript
License: MIT
Stars: 12
Forks: 2
Downloads:
Commits (30d): 0
Language: TypeScript
License: MIT
No risk flags
No risk flags

About graphlit-mcp-server

graphlit/graphlit-mcp-server

Model Context Protocol (MCP) Server for Graphlit Platform

Provides a unified knowledge base by ingesting data from 20+ sources (Slack, Discord, Google Drive, GitHub, Jira, email, etc.) and extracting documents to Markdown and transcribing audio/video automatically. Exposes retrieval, RAG, extraction, and publishing capabilities through 40+ MCP tools—including built-in web crawling and search—enabling AI clients like Cursor and Cline to query and reason over aggregated project knowledge without external tool dependencies.

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