MCP ExplorerExplorer

Riza MCP Server

@riza-ioon 11 days ago
10 MIT
FreeOfficial
Dev Tools
#code interpreter#LLM#tools
[Riza](https://riza.io) offers an isolated code interpreter for your LLM-generated code.

Overview

What is Riza MCP Server

Riza MCP Server is an implementation that wraps the Riza API and presents endpoints as individual tools, allowing for isolated code interpretation for LLM-generated code.

Use cases

Riza MCP Server can be used for securely creating, executing, editing, and managing code tools generated by LLMs. It is suitable for development, testing, and operationalizing machine learning models and other script-based applications.

How to use

To use the Riza MCP Server, configure it with your Riza API key in your MCP client, typically via a JSON configuration file. Once set up, utilize various provided tools to create, execute, edit, and manage code.

Key features

Key features of Riza MCP Server include tools for creating and executing custom code, fetching and editing saved tools, listing available tools, and executing arbitrary code without saving it. This offers flexibility and security when working with generated code.

Where to use

Riza MCP Server is ideal for environments that need secure and isolated execution of code, such as in AI development and deployment scenarios, educational settings for coding exercises, or anywhere LLM-generated code needs reliable testing.

Content

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.

Tools

create_tool
Create a new tool. This tool will be used to create new tools. You can use the tools you have created to perform tasks.
fetch_tool
Fetch a tool, including its source code.
edit_tool
Edit a tool, including its source code. Omit properties that you do not want to change.
execute_code
Execute arbitrary Typescript or Python code.
list_tools
Lists the tool definitions of all self-written tools available for use. These tools can be used by calling `use_tool` with the name and input.
execute_tool
Executes a tool. This tool will be used to execute a self-written tool.

Comments