
MCP Gateway for RFK Jr Endpoints
A Model Context Protocol gateway that connects to RFK Jr-related endpoints, supporting both STDIO and SSE transport methods.
README
MCP Gateway for Voitta
This MCP server provides a gateway to the Voitta library, allowing you to use Voitta's capabilities through the Model Context Protocol (MCP). It supports both STDIO and SSE transports.
Requirements
- Python 3.10+
- Dependencies listed in
requirements.txt
(including voitta)
Installation
- Clone this repository
- Install dependencies:
pip install -r requirements.txt
Configuration
The server reads the Voitta configuration from a YAML file. By default, it looks for the file at /Users/gregory/g/projects/llm/roma/voitta-example/config/voitta.yaml
, but you can specify a different path using the CONFIG_PATH
environment variable.
The configuration file should follow the format expected by the Voitta library. Refer to the Voitta documentation for details on the configuration format.
Usage
Running with VSCode
You can run the server directly from VSCode using the provided launch configuration.
Running from the Command Line
Run the server using:
python server.py
For HTTP mode (SSE transport):
FASTMCP_HTTP=1 PORT=10000 python server.py
Testing with MCP Inspector
The MCP Inspector is a useful tool for testing and debugging MCP servers. Here's how to use it with the Voitta Gateway:
-
Start the MCP Inspector:
npx @modelcontextprotocol/inspector
-
Open the inspector console at http://localhost:5173
-
For STDIO transport (recommended for testing), use one of these options:
Option 1: Using python directly
- Select "STDIO" as the Transport Type
- Set the Command to:
python
(orpython3
depending on your system) - Set the Arguments to:
server.py
Option 2: Using uv
- Select "STDIO" as the Transport Type
- Set the Command to:
uv
- Set the Arguments to:
run --with fastmcp --with pyyaml --with voitta --with pydantic server.py
Option 3: Using fastmcp with full paths
- Select "STDIO" as the Transport Type
- Set the Command to:
/path/to/your/fastmcp
(e.g.,/Users/gregory/g/projects/llm/roma/mcp-voitta-gateway/.venv/bin/fastmcp
) - Set the Arguments to:
run /full/path/to/server.py
(e.g.,run /Users/gregory/g/projects/llm/roma/mcp-voitta-gateway/server.py
)
Option 4: Using cd and fastmcp
- Select "STDIO" as the Transport Type
- Set the Command to:
bash
(or your shell) - Set the Arguments to:
-c "cd /Users/gregory/g/projects/llm/roma/mcp-voitta-gateway && fastmcp run server.py"
-
Click "Connect" to establish a connection to the server
-
Once connected, you can:
- View available tools under the "Tools" tab
- Access the
voitta://tools
resource to see all Voitta tools - Test tools by providing input parameters and executing them
- View the server logs in the console output
For HTTP/SSE transport:
- Start the server in HTTP mode:
FASTMCP_HTTP=1 PORT=10000 python server.py
- In the MCP Inspector, select "SSE" as the Transport Type
- Set the URL to:
http://localhost:10000
- Click "Connect"
Available Tools and Resources
The server automatically registers all tools provided by the Voitta library. You can get a list of available tools using the voitta://tools
resource.
Additionally, the server provides the following MCP tools:
get_voitta_tool_info
: Get detailed information about a specific Voitta tool, including its parameters and descriptions.
Installation for LLM Assistants
Install for Claude
fastmcp install server.py --name "voitta-gateway"
Install for Cline
Follow the Cline documentation for installing MCP servers.
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.