Riza MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Riza MCP Server execute python to calculate factorial of 5"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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 usingexecute_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 toolscreate_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
Scored across 6 tools
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.
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.
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.
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
Related MCP Connectors
Build Apps and run code in 30 languages — sandboxed, with persistent sessions for agent loops.
Run Python code in a secure sandbox without local setup. Declare inline dependencies and execute s…
Run Python code from natural language prompts, with optional PyPI package install.
Code intelligence for LLMs. Analyze, search, and retrieve code from any public git repository.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables LLMs to execute Python code securely in a sandboxed environment. Supports configurable restrictions like no network access and returns results including files.MIT
- AlicenseAqualityDmaintenanceEnables AI assistants to securely execute Python and JavaScript code in sandboxed environments, with file management and package installation.771 npmMIT
- FlicenseNot gradedqualityDmaintenanceEnables LLMs to execute Python code in a restricted sandbox for calculations and data analysis, without giving them a real shell.-
- FlicenseNot gradedqualityNot gradedmaintenanceEnables LLMs to interact with Python environments, execute code or scripts, manage packages, and read/write files within an isolated working directory.-