Skip to main content
Glama
Riza MCP Server

Riza MCP Server

by ampcome-mcps

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.

Available Tools

6 tools
create_toolC

Create a new tool. This tool will be used to create new tools. You can use the tools you have created to perform tasks.

Inputs: code (required), name (required), language (required), description (required), +1 more.

edit_toolA

Edit a tool, including its source code. Omit properties that you do not want to change.

Inputs: code (required), tool_id (required), language (required), input_schema (required), +2 more.

execute_codeB

Execute arbitrary Typescript or Python code.

Inputs: code, language.

execute_toolB

Executes a tool. This tool will be used to execute a self-written tool.

Inputs: input (required), tool_id (required).

fetch_toolA

Fetch a tool, including its source code.

Inputs: tool_id.

list_toolsA

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.

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.5/5.0

    Scored across 6 tools

    Disambiguation5/5

    Each tool has a distinct role: create, fetch, edit, list, and execute self-written tools, plus execute_code for arbitrary ad-hoc code. The only potentially overlapping pair, execute_code and execute_tool, is clearly separated by whether the code is a saved tool or not.

    Naming Consistency5/5

    All tool names follow a consistent snake_case verb_noun pattern, such as create_tool, fetch_tool, edit_tool, and execute_tool. The minor pluralization in list_tools is predictable and does not break the naming convention.

    Tool Count5/5

    Six tools is well-suited to the server's purpose of managing and executing self-written tools. Each tool contributes a necessary operation without unnecessary bloat.

    Completeness3/5

    The set covers create, read, update, list, and execute, but lacks a delete/remove operation, which is a notable lifecycle gap. Additionally, list_tools references a use_tool that does not exist in the exposed tool set, though execute_tool appears to fill that role.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables LLMs to execute Python code securely in a sandboxed environment. Supports configurable restrictions like no network access and returns results including files.
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables LLMs to execute Python code in a restricted sandbox for calculations and data analysis, without giving them a real shell.
      -