Warpcast MCP Server
Enables interaction with Warpcast (Farcaster) through Claude, allowing users to post casts, search and read content, get trending posts, and manage channel subscriptions using natural language.
README
Warpcast MCP Server
A Model Context Protocol (MCP) server for Warpcast integration that allows you to use Claude to interact with your Warpcast account.
The implementation now follows the FastMCP style server from the MCP Python SDK.
Features
- Post casts to your Warpcast account
- Read casts from Warpcast
- Search casts by keyword or hashtag
- Browse and interact with channels
- Follow/unfollow channels
- Get trending casts
Warpcast API https://docs.farcaster.xyz/reference/warpcast/api
Usage
mcp-warpcast-server is usually launched automatically by Claude Desktop's MCP client when the Warpcast tools are configured.
After the server starts you can ask Claude to:
- "Post a cast about [topic]"
- "Read the latest casts from [username]"
- "Search for casts about [topic]"
- "Show me trending casts on Warpcast"
- "Show me popular channels on Warpcast"
- "Get casts from the [channel] channel"
- "Follow the [channel] channel for me"
Available Tools
This MCP server provides several tools that Claude can use:
- post-cast: Create a new post on Warpcast (max 320 characters)
- get-user-casts: Retrieve recent casts from a specific user
- search-casts: Search for casts by keyword or phrase
- get-trending-casts: Get the currently trending casts on Warpcast
- get-all-channels: List available channels on Warpcast
- get-channel: Get information about a specific channel
- get-channel-casts: Get casts from a specific channel
- follow-channel: Follow a channel
- unfollow-channel: Unfollow a channel
Setup
Claude Desktop normally launches this server for you when the Warpcast tools are configured. The steps below are only needed if you want to run the server manually for development.
-
Create a Python virtual environment (Python 3.11 or newer is recommended):
python3 -m venv venv source venv/bin/activate -
Install dependencies (the requirements include the MCP Python SDK):
pip install -r requirements.txt -
Provide a Warpcast API token:
- Log in to Warpcast and open Settings > Developer.
- Click Create API Token and copy the value.
- Add
WARPCAST_API_TOKENunder theenvsection of your Claude desktop configuration. - If starting the server manually, you can instead export the token in your shell:
export WARPCAST_API_TOKEN=YOUR_TOKEN
The server validates this variable on startup. If it is missing, a warning is logged and authorized requests will respond with HTTP 500 errors.
-
(Optional) Start the server manually: The
appvariable exported frommain.pyis created usingmcp.streamable_http_app()so it can be served by any ASGI server.uvicorn main:app --reload
The server exposes HTTP endpoints matching the tools listed above and a standard /mcp endpoint provided by FastMCP.
Using with Claude Desktop
Follow these steps to access the Warpcast tools from Claude's desktop application:
- Start the server (or let Claude launch it) using the setup instructions above.
- Open your Claude configuration file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
- macOS:
- Add the Warpcast server under the
mcpServerskey. Replace the path with the location of this repository:
{
"mcpServers": {
"warpcast": {
"command": "uvicorn",
"args": [
"--app-dir",
"/ABSOLUTE/PATH/TO/mcp-warpcast-server",
"main:app",
"--port",
"8000"
],
"url": "http://localhost:8000/mcp",
"env": {
"WARPCAST_API_TOKEN": "YOUR_API_TOKEN"
}
}
}
}
Specifying a url tells Claude Desktop to communicate with the server over HTTP using Server-Sent Events instead of standard input and output.
If you omit url, Claude Desktop defaults to communicating via standard input and output (stdio), which will not work with this server.
- Save the file and restart Claude Desktop. You should now see a hammer icon in the chat input that lets you use the Warpcast tools.
Running Tests
Unit tests are written with pytest and use FastAPI's TestClient (installed via fastapi[testclient]).
Create a virtual environment, install dependencies and run the suite:
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
make test # or simply `pytest`
The tests mock the Warpcast API layer so no network connection is required.
MCP Compatibility
This server uses the official MCP Python SDK and is fully compatible with the Model Context Protocol. Clients can connect to the /mcp endpoint provided by FastMCP and interact with the tools defined here.
License
This project is licensed under the MIT License.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.