activitypub
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.
claude mcp add --transport stdio cameronrye-activitypub-mcp npx -y activitypub-mcp start
How to use
ActivityPub MCP Server is a Model Context Protocol (MCP) server that enables LLMs to explore and interact with the Fediverse via standardized MCP tools, resources, and prompts. It exposes a suite of MCP resources and 53 tools (21 read-only discovery tools, 28 authenticated content/tools for posting and management, and 4 export tools) that let an LLM retrieve timelines, discover remote actors, follow accounts, post content, manage media and polls, and export data in multiple formats. The server is designed to be LLM-friendly, with MCP prompts tailored for fediverse exploration and content strategy, and it supports both standard HTTP transport and a local stdio mode for Claude Desktop integrations. To begin, install the package (activitypub-mcp) and run the MCP server; then you can interact with the MCP Inspector or query tools to discover actors, timelines, and instances, or to perform authenticated actions like posting or exporting data.
How to install
Prerequisites
- Node.js 18+ (LTS recommended)
- npm or yarn
- Git
One-Click Installation
- Use npx to install and run the server:
# Install directly with npx (recommended)
npx activitypub-mcp install
- Or clone and run setup:
git clone https://github.com/cameronrye/activitypub-mcp.git
cd activitypub-mcp
npm run setup
Platform-specific installation Windows (PowerShell):
# Clone and setup
git clone https://github.com/cameronrye/activitypub-mcp.git
cd activitypub-mcp
npm run setup:windows
# Or run PowerShell script directly
.\scripts\setup.ps1
macOS/Linux (Bash):
# Clone and setup
git clone https://github.com/cameronrye/activitypub-mcp.git
cd activitypub-mcp
npm run setup:unix
# Or run bash script directly
bash scripts/setup.sh
Manual Installation
- Clone and install dependencies:
git clone https://github.com/cameronrye/activitypub-mcp.git
cd activitypub-mcp
npm install
- Configure environment: Windows:
# Copy environment template
copy .env.example .env
# Edit configuration (optional)
notepad .env
macOS/Linux:
# Copy environment template
cp .env.example .env
# Edit configuration (optional)
nano .env
- Start the MCP server:
# Start the MCP server (no local ActivityPub server needed)
npm run mcp
Testing the Setup
- Test MCP server with MCP Inspector:
# Install MCP Inspector
npm install -g @modelcontextprotocol/inspector
# Connect to the MCP server
mcp-inspector
Claude Desktop Integration To use with Claude Desktop, locate Claude Desktop config as described in the README and configure the MCP server connection accordingly.
Additional notes
Tips and common considerations:
- The server exposes a broad set of resources, tools, and prompts; use MCP Inspector to explore available endpoints and test tool invocations.
- If you encounter port or environment issues, adjust PORT and MCP_LOG_LEVEL in a local .env file.
- For production deployments, consider the HTTP transport mode for enterprise reliability and enable appropriate security and rate-limiting settings.
- Ensure you have the required permissions and access tokens when using authenticated tools (posting, timelines, or exports).
- The project is TypeScript-based and ships with a typed MCP surface; review the 53 tools and 11 prompts to understand capabilities before crafting complex prompts.
- Use the Export Tools to export timelines, threads, or accounts in JSON, Markdown, or CSV formats for downstream workflows.
Related MCP Servers
context7
Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
obsidian -tools
Add Obsidian integrations like semantic search and custom Templater prompts to Claude or any MCP client.
MiniMax -JS
Official MiniMax Model Context Protocol (MCP) JavaScript implementation that provides seamless integration with MiniMax's powerful AI capabilities including image generation, video generation, text-to-speech, and voice cloning APIs.
mcp-bundler
Is the MCP configuration too complicated? You can easily share your own simplified setup!
akyn-sdk
Turn any data source into an MCP server in 5 minutes. Build AI-agents-ready knowledge bases.
promptboard
The Shared Whiteboard for Your AI Agents via MCP. Paste screenshots, mark them up, and share with AI.