Riza MCP Server

What does “Riza” MCP Server do?

The Riza MCP Server serves as a bridge between AI assistants and the Riza platform’s isolated code interpreter environment. By implementing the Model Context Protocol (MCP), the Riza MCP server exposes the Riza API as a set of easy-to-use tools, enabling AI agents and developers to perform advanced code execution, tool management, and workflow automation securely and programmatically. This protocol-driven interface lets LLMs (Large Language Models) interact with Riza for tasks such as writing, editing, executing, and listing custom code tools, as well as running arbitrary code in a sandboxed environment. The integration enhances development workflows by automating repetitive coding tasks, ensuring secure execution, and enabling seamless tool creation and management directly from the AI interface.

List of Prompts

No information about prompt templates is present in the repository.

List of Resources

No explicit MCP resources are documented in the repository.

List of Tools

• create_tool: Allows the LLM or user to write code and save it as a reusable tool using the Riza Tools API.
• fetch_tool: Retrieves saved Riza tools, along with their source code, enabling further inspection or editing.
• execute_tool: Executes a previously saved tool securely using Riza’s code interpreter API.
• edit_tool: Modifies the source code or configuration of an existing saved tool.
• list_tools: Lists all the available saved tools accessible via the Riza API.
• execute_code: Executes arbitrary code safely in Riza’s isolated code interpreter, without the need to save it as a tool.

Use Cases of this MCP Server

• Secure Code Execution: Run arbitrary code in an isolated environment, ensuring security and preventing access to sensitive systems or data.
• Automated Tool Creation: Allow LLMs or users to write and save reusable code tools, streamlining repetitive or complex coding workflows.
• Tool Management: Fetch, edit, and list user-defined tools for easier maintenance and collaboration within development teams.
• Integration with AI Agents: Enable AI agents to interact programmatically with the Riza code interpreter, powering advanced automation and agentic behaviors.
• Rapid Prototyping: Execute code snippets or entire tools instantly, facilitating quick iterations, debugging, and proof-of-concept development.

How to set it up

Windsurf

1. Ensure you have Node.js installed.
2. Obtain a free Riza API key from your Riza Dashboard.
3. Open your Windsurf configuration file.
4. Add the Riza MCP server to the mcpServers section:

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

5. Save your changes and restart Windsurf.
6. Verify setup by checking tool availability in the interface.

Claude

1. Install Node.js if not already present.
2. Acquire your Riza API key from the Riza Dashboard.
3. Edit the Claude configuration to include the Riza MCP server:

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

4. Save the configuration and restart Claude.
5. Confirm access by listing available tools via the Claude UI.

Cursor

1. Make sure Node.js is installed.
2. Retrieve your Riza API key from the Riza Dashboard.
3. Open the Cursor settings file and add the following:

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

4. Save and restart Cursor.
5. Check that the Riza MCP server is registered as an available tool provider.

Cline

1. Install Node.js if it is not already installed.
2. Obtain your Riza API key from Riza Dashboard.
3. Add the following snippet to your Cline configuration file:

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

4. Save and restart Cline.
5. Verify the server is running and tools are accessible.

Securing API Keys

• Always provide your RIZA_API_KEY using environment variables within the configuration:

  "env": {
    "RIZA_API_KEY": "your-api-key"
  }
  

• For extra security, do not hardcode API keys in source files. Use environment-specific configuration or secrets management.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "riza-server": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “riza-server” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

| Roots support: ⛔ No mention found |

Based on the available information, the Riza MCP server exposes a clear set of tools and provides good setup documentation, but lacks explicit prompt templates, resource definitions, and any reference to roots or sampling features. Its documentation is minimal but functional.

Our opinion

Riza MCP is a straightforward, code-execution-focused MCP server implementation, making it well-suited for secure automation and tool management in development pipelines. However, it lacks depth in documentation regarding prompts, resources, roots, and sampling, which may limit its flexibility for broader MCP use cases. Overall, it scores as a solid, specialized server for its intended domain, but could benefit from more comprehensive MCP documentation and feature support.

MCP Score