​
What’s MCP?

Model Context Protocol (MCP) is an open standard developed by Anthropic that streamlines how AI models connect with different data sources and tools.

MCP defines specs for MCP clients and MCP servers. Today, MCP clients include Claude Desktop, IDEs like Cursor, and custom client implementations written in frameworks like PydanticAI.

Riza provides a remote and a local MCP server that you can connect to MCP clients.

​
Remote MCP server

We offer a hosted Model Context Protocol (MCP) server so you can connect an agent to our Code Interpreter without downloading and running additional code.

You can use this server with any framework or client that supports remote MCP servers.

​
Get the MCP server URL

  1. Sign up for Riza. You’ll need a Riza account to use the remote MCP server.
  2. Get your Riza MCP URL. Visit the MCP page in the Riza dashboard. There, you’ll see your URL, which includes your secret key: https://mcp.riza.io/code-interpreter?secret=YOUR_RIZA_REMOTE_MCP_SECRET

​
PydanticAI

Here’s how you can use the remote MCP server with PydanticAI:

from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

server = MCPServerHTTP(url="https://mcp.riza.io/code-interpreter?secret=YOUR_RIZA_REMOTE_MCP_SECRET")
agent = Agent('openai:gpt-4o', mcp_servers=[server])

async def main():
    async with agent.run_mcp_servers():
        result = await agent.run('How many days between 2000-01-01 and 2025-03-18?')
    print(result.data)
    #> There are 9,208 days between January 1, 2000, and March 18, 2025.

if __name__ == "__main__":
    import asyncio
    asyncio.run(main())

​
Cursor

To add the remote MCP server to Cursor, edit your Cursor MCP server configuration file to include the following snippet:

{
  "mcpServers": {
    "riza-server": {
      "url": "https://mcp.riza.io/code-interpreter?secret=YOUR_RIZA_REMOTE_MCP_SECRET"
    }
  }
}

​
Local MCP server

We offer an MCP server that you can run locally. You can view the code on GitHub.

You can use this with any framework or client that supports local stdio MCP servers, such as Claude Desktop.

​
Prerequisites

  1. Sign up for Riza. You’ll need a Riza API key to use the local server.
  2. Install Node.js on your computer. Node is required to download and run the server.

​
PydanticAI

Here’s an example of how to use the local MCP server with PydanticAI:

from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStdio

server = MCPServerStdio(
    'npx', ['@riza-io/riza-mcp'], env={'RIZA_API_KEY': os.getenv('RIZA_API_KEY')})
agent = Agent('openai:gpt-4o', mcp_servers=[server])

async def main():
    async with agent.run_mcp_servers():
        result = await agent.run('How many days between 2000-01-01 and 2025-03-18?')
    print(result.data)
    #> There are 9,208 days between January 1, 2000, and March 18, 2025.

if __name__ == "__main__":
    import asyncio
    asyncio.run(main())

​
Claude Desktop

To run the server with Claude Desktop, edit your Claude MCP server configuration file to include the following snippet:

{
  "mcpServers": {
    "riza-server": {
      "command": "npx",
      "args": [
        "@riza-io/riza-mcp"
      ],
      "env": {
        "RIZA_API_KEY": "your-api-key"
      }
    }
  }
}