typefully
MCP server for Typefully service
claude mcp add --transport stdio pepuscz-typefully-mcp-server /path/to/your/typefully-mcp-server/venv/bin/python -m typefully_mcp_server.server \ --env TYPEFULLY_API_KEY="Your Typefully API key (or configure via keychain / environment as described)"
How to use
This MCP server provides an integration with the Typefully API, enabling automated draft creation and management from your MCP-enabled assistants. You can create drafts that automatically thread into multi-tweet sequences, schedule posts for a specific time or the next available slot, and optionally enable AutoRT (auto-retweet) or AutoPlug features. In addition, you can retrieve recently scheduled drafts or recently published drafts with optional content filtering to focus on tweets or threads. Use the available MCP actions to orchestrate Typefully workflows from your AI assistant, enabling content generation, scheduling, and publication control in a unified interface.
How to install
Prerequisites:
- Python 3.10 or higher
- A Typefully account with API access and a valid API key
- Access to the MCP client configuration (Cursor, Claude Desktop, etc.)
Install from source:
- Clone the repository and navigate to it:
git clone <repository-url>
cd typefully-mcp-server
- Create and activate a virtual environment:
python3 -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
- Install the package in editable mode:
pip install -e .
- Prepare MCP configuration (see below) and start using the server with your MCP client. Optionally install development dependencies for testing:
pip install -e ".[dev]"
Configuration reference (example you would place in your MCP client configuration):
{
"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"
}
}
}
Running tests (optional):
source venv/bin/activate # On Windows: venv\Scripts\activate
pytest
Additional notes
Notes and tips:
- API key management: You can store the Typefully API key in macOS Keychain (recommended) or use environment variables. If both are present, environment variables take precedence for compatibility.
- API key usage: If you choose to store in environment variables, set TYPEFULLY_API_KEY in your environment or in the MCP configuration as shown in the example.
- Keychain setup (macOS): Service: typefully-mcp-server, Account: api_key, Password: your Typefully API key. See CURSOR_SETUP.md for detailed steps.
- Scheduling: When creating a draft, you can specify schedule_date with an ISO timestamp or use next-free-slot to auto-allocate the next available window.
- Content formatting: Use four consecutive newlines to separate tweets within a single draft for multi-tweet threads.
- Troubleshooting: Ensure the virtual environment is active when running the server and that the API key has the necessary Typefully permissions. Check server logs for authentication errors or API rate limits.
Related MCP Servers
web-eval-agent
An MCP server that autonomously evaluates web applications.
mcp-neo4j
Neo4j Labs Model Context Protocol servers
Gitingest
mcp server for gitingest
zotero
Model Context Protocol (MCP) server for the Zotero API, in Python
fhir
FHIR MCP Server – helping you expose any FHIR Server or API as a MCP Server.
unitree-go2
The Unitree Go2 MCP Server is a server built on the MCP that enables users to control the Unitree Go2 robot using natural language commands interpreted by a LLM.