Typefully MCP Server

by pepuscz

351 downloads
Not rated
GitHub

About

A Model Context Protocol (MCP) server that integrates with the Typefully API, allowing AI assistants to create and manage drafts on Typefully. It is intended for developers who use MCP-compatible AI tools like Cursor or Claude Desktop.

Details

Author
pepuscz
Downloads
351
Categories
Other

- Create multi‑tweet threads (separated by four newlines)
- Schedule drafts for a specific date/time or next free slot
- Enable AutoRT and AutoPlug on new drafts
- Retrieve scheduled drafts with optional content filtering
- Retrieve published drafts with optional content filtering
- Securely store API key in macOS Keychain

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Typefully MCP Server
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Install from source with Python 3.10+, configure your Typefully API key via macOS Keychain or an environment variable, then add the MCP server configuration to your MCP client. Once set up, invoke tools such as create_draft, get_scheduled_drafts, and get_published_drafts through natural language commands.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "typefully mcp server": {
            "typefully": {
                "command": "/path/to/your/typefully-mcp-server/venv/bin/python",
                "args": [
                    "-m",
                    "typefully_mcp_server.server"
                ],
                "cwd": "/path/to/your/typefully-mcp-server",
                "env": {
                    "TYPEFULLY_API_KEY": "your_actual_api_key_here"
                }
            }
        }
    }
}

McpServers

{
    "typefully": {
        "command": "/path/to/your/typefully-mcp-server/venv/bin/python",
        "args": [
            "-m",
            "typefully_mcp_server.server"
        ],
        "cwd": "/path/to/your/typefully-mcp-server",
        "env": {
            "TYPEFULLY_API_KEY": "your_actual_api_key_here"
        }
    }
}

Typefully MCP Server

A Model Context Protocol (MCP) server that provides integration with the Typefully API, allowing AI assistants to create and manage drafts on Typefully.

Features

- Create drafts with full support for:
- Multi-tweet threads (using 4 newlines as separator)
- Automatic threadification
- Scheduling (specific date/time or next free slot)
- AutoRT and AutoPlug features
- Share URLs
- Get scheduled drafts with optional filtering
- Get published drafts with optional filtering

Installation

Prerequisites

- Python 3.10 or higher
- A Typefully account with API access
- Your Typefully API key (get it from Settings > Integrations in Typefully)

Install from source

1. Clone this repository:

git clone <repository-url>
cd typefully-mcp-server

2. Create and activate a virtual environment:

python3 -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate

3. Install the package:

pip install -e .

Configuration

API Key Management

This server supports secure API key storage using macOS Keychain. You have two options:

Option 1: macOS Keychain (Recommended) 🔐

Store your API key securely in the macOS System keychain:
- Service: typefully-mcp-server
- Account: api_key
- Password: Your Typefully API key

For detailed keychain setup instructions, see CURSOR_SETUP.md.

Option 2: Environment Variables

You can set the API key as an environment variable or include it directly in your MCP configuration.

Note: Environment variables take priority over keychain storage for compatibility.

MCP Configuration

For detailed MCP client setup instructions (Cursor, Claude Desktop, etc.), see CURSOR_SETUP.md.

Basic MCP configuration example:

{
  "mcpServers": {
    "typefully": {
      "command": "/path/to/your/typefully-mcp-server/venv/bin/python",
      "args": ["-m", "typefully_mcp_server.server"],
      "cwd": "/path/to/your/typefully-mcp-server"
    }
  }
}

Usage

Once configured, the MCP server provides the following tools:

create_draft

Create a new draft in Typefully.

Parameters:
- content (required): The content of the draft. Use 4 consecutive newlines to split into multiple tweets.
- threadify (optional): Automatically split content into multiple tweets
- share (optional): If true, returned payload will include a share_url
- schedule_date (optional): ISO formatted date (e.g., "2024-01-15T10:30:00Z") or "next-free-slot"
- auto_retweet_enabled (optional): Enable AutoRT for this post
- auto_plug_enabled (optional): Enable AutoPlug for this post

Example:

Create a draft with content "Hello from MCP! This is my first automated tweet." and schedule it for next free slot

get_scheduled_drafts

Get recently scheduled drafts from Typefully.

Parameters:
- content_filter (optional): Filter drafts to only include "tweets" or "threads"

Example:

Get my scheduled drafts that are threads only

get_published_drafts

Get recently published drafts from Typefully.

Parameters:
- content_filter (optional): Filter drafts to only include "tweets" or "threads"

Example:

Show me all my recently published tweets

Testing

A test script is included to verify the server functionality:

```bash

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.