- Home
- MCP servers
- Typefully
Typefully
- python
6
GitHub Stars
python
Language
6 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"pepuscz-typefully-mcp-server": {
"command": "/path/to/your/typefully-mcp-server/venv/bin/python",
"args": [
"-m",
"typefully_mcp_server.server"
]
}
}
}You run a Typefully MCP Server locally to automate creating, scheduling, and managing Typefully drafts. This server lets you craft multi-tweet threads, schedule posts, and enable AutoRT or AutoPlug features, all through a lightweight MCP interface.
How to use
To use the server, connect through an MCP client you already use (Cursor, Claude Desktop, or another MCP-capable client). You’ll access the available actions to create drafts, view scheduled items, or review published posts. Use the create_draft action to compose content, split long content into threads with four consecutive newlines, and optionally enable scheduling, sharing, or automation features. You can fetch recently scheduled drafts or recently published drafts using the get_scheduled_drafts and get_published_drafts actions, optionally filtering results by content type (tweets or threads). Ensure your API key is configured for the server so that requests authenticate correctly.
Key concepts you’ll use frequently:
- Draft creation with optional scheduling and sharing
- Thread handling for multi-tweet content
- AutoRT and AutoPlug features to extend reach and engagement
- Filtering when listing drafts to find exactly what you need
How to install
Prerequisites you need before installing the server:
Install from source with these steps:
clone the project
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 .
Configure the MCP client for your runtime. The following is a representative configuration you would place in your MCP config file to run the server locally.
{
"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"
}
}
}
Configuration and security
API key management options let you store the key securely or provide it via environment variables. Secure storage commonly uses the macOS Keychain with the following identifiers (when you choose this path): Service: typefully-mcp-server, Account: api_key, Password: your Typefully API key. If you prefer, you can supply the API key through environment variables, which take precedence for compatibility.
Proceed with the MCP configuration once you have the API key ready. The server supports creating drafts, listing scheduled drafts, and listing published drafts as described in the usage section.
Note: If you need to verify integration in a dev environment, you can run tests or a test script after activating your virtual environment to confirm API connectivity (requires a configured API key). Use the provided test script to check connectivity.
Testing
Activate your virtual environment and run the test to verify API connectivity.
# Activate the environment
source venv/bin/activate # On Windows: venv\Scripts\activate
# Run the API connectivity test (requires API key configured)
python test_read_api.py
Development notes
Project structure highlights the MCP server files, including the server implementation, API client, keychain integration, and type definitions. When developing, install development dependencies and run tests to ensure changes behave as expected.
Key components you may interact with during development:
- server.py: Main MCP server implementation
- client.py: Typefully API client used by the server
- keychain.py: Secure keychain integration for API keys
- types.py: Type definitions used across the project
Available tools
create_draft
Create a new Typefully draft with content, enabling options like threadification, sharing, scheduling, and automation (AutoRT/AutoPlug) as needed.
get_scheduled_drafts
Retrieve recently scheduled drafts with optional content filtering to show only tweets or threads.
get_published_drafts
Retrieve recently published drafts with optional content filtering to show only tweets or threads.