Mastodon MCP Server

A Model Context Protocol (MCP) server for Mastodon, allowing AI models to interact with your Mastodon account.

Features

• get_home_timeline: View your home feed.
• post_status: Create new toots/statuses.
• get_notifications: Check your mentions and interactions.

Setup

1. Get Mastodon Credentials

1. Go to your Mastodon instance (e.g., `https://leaseysocial.com`).
2. Navigate to Preferences > Development > New Application.
3. Give it a name (e.g., "MCP Server") and ensure it has `read` and `write` scopes.
4. Copy your Access Token.

2. Configuration

Create a `.env` file in the project root: ```env MASTODON_INSTANCE=https://leaseysocial.com MASTODON_ACCESS_TOKEN=your_access_token_here ```

3. Installation

```bash npm install npm run build ```

Integration

Cursor

To use this with Cursor:

1. Open Cursor Settings.
2. Go to Models > MCP.
3. Click + Add New MCP Server.
4. Set Type to `command`.
5. Name: `Mastodon`.
6. Command: `node /path/to/mastodon-mcp-server/dist/index.js`.

Claude Desktop

Add this to your `claude_desktop_config.json`: ```json { "mcpServers": { "mastodon": { "command": "node", "args": ["/path/to/mastodon-mcp-server/dist/index.js"], "env": { "MASTODON_INSTANCE": "https://leaseysocial.com", "MASTODON_ACCESS_TOKEN": "your_access_token_here" } } } } ```

Poke.com

To upload to Poke:

1. Go to poke.com/integrations/new.
2. Choose Custom MCP.
3. Point it to your GitHub repository or provide the connection details.

Deployment

This project is designed to be shippable. You can host it on any provider that supports Node.js or run it locally via stdio.

---

Created for Maria Reyes (teknoflame).