Warpcast
An MCP server for interacting with the Warpcast social network.
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.
Serveurs connexes
Telegram Bot Gateway
A simple gateway to interact with Telegram bots using MCP and a REST API, enabling integration with LLMs.
Slack
The most powerful MCP server for Slack Workspaces. This integration supports both Stdio and SSE transports, proxy settings and does not require any permissions or bots being created or approved by Workspace admins 😏.
Telegram
Interact with the Telegram API to send and receive messages.
JustCall MCP Server
The JustCall Model Context Protocol (MCP) Server lets Large Language Models (LLMs) and AI agents make real-world voice calls and send SMS directly through JustCall’s APIs — securely, contextually, and programmatically.
MCP gRPC Transport
A gRPC transport for MCP, enabling communication between clients and remote MCP servers.
nadanada_me
A public MCP server that gives AI agents access to real UK carrier phone numbers for SMS verification. Agents can rent disposable or rental numbers, pay Lightning invoices, and read incoming SMS, all through standard MCP tool calls with no authentication required.
Email
This server enables users to send emails through various email providers, including Gmail, Outlook, Yahoo, Sina, Sohu, 126, 163, and QQ Mail. It also supports attaching files from specified directories, making it easy to upload attachments along with the email content.
Telnyx
Official Telnyx remote MCP server for AI agents.
WhatsApp Web
An MCP server for interacting with WhatsApp Web, allowing you to send and receive messages.
MCP Discord Agent Communication
Enables asynchronous communication between AI agents and users through Discord, ideal for long-running tasks.