Typefully MCP Server

What is Typefully MCP Server?

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.

How to use Typefully MCP Server?

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.

Key features of Typefully MCP Server

• 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

Use cases of Typefully MCP Server

• Compose and schedule a Twitter thread entirely through an AI assistant
• Automatically draft and queue posts using a scheduled next‑free slot
• Review recently published tweets or threads via a chat interface
• Filter and list only threads from your scheduled drafts

FAQ from Typefully MCP Server

What prerequisites are needed to run the server?

Python 3.10 or higher, a Typefully account with API access, and a Typefully API key (available from Settings > Integrations in Typefully).

How do I store my Typefully API key?

You can store it in the macOS Keychain (Service: typefully-mcp-server, Account: api_key) or set it as an environment variable. Environment variables take priority over keychain storage.

What tools does the server provide?

The server provides create_draft, get_scheduled_drafts, and get_published_drafts. Each tool accepts optional parameters for content filtering, scheduling, and threading.

Can I filter drafts by type?

Yes. Both get_scheduled_drafts and get_published_drafts accept a content_filter parameter that accepts "tweets" or "threads" to narrow results.

How do I test the server after setup?

Run the included test_read_api.py script after configuring your API key and activating the virtual environment. It verifies API connectivity.