Riza MCP Server

What is Riza MCP Server about?

Provides a Model Context Protocol (MCP) server that converts Riza’s code‑interpreter capabilities into discrete tool endpoints. LLMs can invoke these endpoints to create, fetch, edit, list, and execute saved tools or run arbitrary code safely.

How to use Riza MCP Server?

1. Install the server via npx:

   npx @riza-io/riza-mcp
   

2. Supply a valid Riza API key through the RIZA_API_KEY environment variable.
3. Configure your MCP client (e.g., Claude Desktop) with the following JSON snippet:

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

4. From your LLM, call the exposed tool endpoints (e.g., create_tool, execute_tool).

Key Features of Riza MCP Server

• create_tool: Save new code as a reusable tool via Riza’s Tools API.
• fetch_tool: Retrieve existing tool definitions and source code.
• execute_tool: Run a saved tool in Riza’s isolated interpreter.
• edit_tool: Update the source of a stored tool.
• list_tools: Enumerate all saved tools for a user/account.
• execute_code: Run ad‑hoc code without persisting it as a tool.
• Simple npm‑based deployment using npx.

Use Cases of Riza MCP Server

• LLM‑driven automation: Allow an LLM to generate and run custom scripts on demand.
• Tool marketplace: Create, share, and execute reusable code snippets across projects.
• Secure sandboxed execution: Run untrusted code safely via Riza’s isolated interpreter.
• Iterative development: Fetch and edit tools directly from the LLM without manual code handling.

FAQ from the Riza MCP Server

• Do I need to install anything locally? No, the server runs via npx which fetches the package at runtime.
• What authentication is required? Set the RIZA_API_KEY environment variable with a key from the Riza Dashboard.
• Can I execute arbitrary code without saving it? Yes, use the execute_code endpoint for one‑off executions.
• Is there a limit on tool size or execution time? Limits are enforced by Riza’s backend; refer to the Riza API documentation for specifics.
• How do I list all my tools? Call the list_tools endpoint; it returns metadata for each saved tool.

Riza MCP Server

Riza offers an isolated code interpreter for your LLM-generated code.

Our MCP server implementation wraps the Riza API and presents endpoints as individual tools.

Configure with Claude Desktop as below, or adapt as necessary for your MCP client. Get a free Riza API key in your Riza Dashboard.

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

The Riza MCP server provides several tools to your LLM:

• create_tool: Your LLM can write code and save it as a tool using the Riza Tools API. It can then execute these tools securely on Riza using execute_tool.
• fetch_tool: Your LLM can fetch saved Riza tools, including source code, which can be useful for editing tools.
• execute_tool: Executes a saved tool securely on Riza's code interpreter API.
• edit_tool: Edits an existing saved tool.
• list_tools: Lists available saved tools.
• execute_code: Executes arbitrary code safely on Riza's code interpreter API, without saving it as a tool.