mcpField
R
Riza MCP Server

Riza MCP Server

Local
github.com/riza-ioDeveloper Tools13Updated 97w ago
Repository

About Riza MCP Server

Riza MCP Server wraps the Riza API as tools for running LLM-generated code in Riza's isolated code interpreter. It can create, retrieve, edit, and run saved tools, as well as execute unsaved code.

Key features

  1. 01Create and save code tools
  2. 02Fetch and edit saved tools
  3. 03List available tools
  4. 04Securely execute saved tools
  5. 05Run code without saving it

Use cases

  1. 01Turn LLM-written code into reusable tools
  2. 02Run saved custom tools in isolation
  3. 03Execute one-off code without saving

MCP support

The MCP server exposes Riza API endpoints as tools for MCP clients, including code execution and management of saved tools.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "riza": {
      "command": "npx",
      "args": [
        "-y",
        "@riza-io/riza-mcp"
      ],
      "env": {
        "RIZA_API_KEY": "<RIZA_API_KEY>"
      }
    }
  }
}
Run commandnpx -y @riza-io/riza-mcp
Environment variables to set
RIZA_API_KEYSecret

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@riza-io/riza-mcp

Tools

6

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
namestringYesThe name of the tool you are writing. This is what you will use to call the tool.
descriptionstringYesA description of the tool you are writing. This will help you or other agents or people pick the appropriate tool in the future.
codestringYesThe Typescript code for the tool you are writing. The code should be a valid Typescript function named `execute` that takes one argument called `input`. When called, the `input` provided will match the schema of the `input_schema` of the tool.
input_schemaobjectYesThe input schema for the tool. This must be provided as a valid JSON Schema object.
languagestringYesThe language of the tool you are writing. This must be either 'TYPESCRIPT' or 'PYTHON'.

Details

From the project README

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.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.