Eunomia MCP Server

What does “Eunomia” MCP Server do?

Eunomia MCP Server is an extension of the Eunomia framework that connects Eunomia instruments with Model Context Protocol (MCP) servers. Its primary purpose is to orchestrate data governance policies—such as Personally Identifiable Information (PII) detection or user access control—across text streams handled by LLM-based (Large Language Model) applications. By integrating with the MCP ecosystem, Eunomia MCP Server enables developers to enforce data policies on top of LLM or other text-based workflows and orchestrate communication between multiple servers using the MCP standard. This adds a robust layer of security and compliance, making it easier to govern data flows in AI-driven environments.

List of Prompts

No prompt templates are mentioned in the repository or documentation.

List of Resources

No explicit MCP resources are detailed in the repository or documentation.

List of Tools

No clear list of MCP tools is provided in the repository or documentation.

Use Cases of this MCP Server

• Data Governance in LLM Pipelines
  Eunomia MCP Server can enforce data governance policies such as PII detection and redaction in LLM-based text pipelines.

• Multi-Server Orchestration
  Developers can orchestrate multiple external MCP servers, ensuring coordinated policy enforcement across distributed systems.

• Integration with External Tools
  The server can connect with other MCP-based services (e.g., a web-browser-mcp-server) to expand the range of data governance and processing capabilities.

• Automated Policy Enforcement
  By defining instruments (such as PiiInstrument), organizations can ensure sensitive information is consistently handled according to policy.

How to set it up

Windsurf

1. Ensure you have Node.js and uv installed.
2. Clone the Eunomia MCP Server repository:
   git clone https://github.com/whataboutyou-ai/eunomia-mcp-server.git
3. In your Windsurf configuration file, add the Eunomia MCP Server to your mcpServers list:
4. Add the following JSON to your configuration:

   {
     "mcpServers": {
       "eunomia-mcp-server": {
         "command": "uv",
         "args": ["tool", "run", "orchestra_server"],
         "env": {
           "REQUEST_TIMEOUT": "30"
         }
       }
     }
   }
   

5. Save the configuration and restart Windsurf.

Claude

1. Install prerequisites (Node.js, uv).
2. Clone the repository.
3. Edit Claude’s configuration to include:

   {
     "mcpServers": {
       "eunomia-mcp-server": {
         "command": "uv",
         "args": ["tool", "run", "orchestra_server"],
         "env": {
           "REQUEST_TIMEOUT": "30"
         }
       }
     }
   }
   

4. Save and restart Claude.
5. Verify by running a test query.

Cursor

1. Ensure you have the latest Cursor version and dependencies.
2. Add the Eunomia MCP Server into the configuration file:

   {
     "mcpServers": {
       "eunomia-mcp-server": {
         "command": "uv",
         "args": ["tool", "run", "orchestra_server"],
         "env": {
           "REQUEST_TIMEOUT": "30"
         }
       }
     }
   }
   

3. Save, restart Cursor, and test.

Cline

1. Install Node.js and uv if not already present.
2. Clone the Eunomia MCP Server repository.
3. Update your Cline configuration file as follows:

   {
     "mcpServers": {
       "eunomia-mcp-server": {
         "command": "uv",
         "args": ["tool", "run", "orchestra_server"],
         "env": {
           "REQUEST_TIMEOUT": "30"
         }
       }
     }
   }
   

4. Save and restart the Cline server.
5. Confirm integration by running a sample MCP command.

Securing API keys:
Use environment variables in your configuration:

{
  "mcpServers": {
    "eunomia-mcp-server": {
      "command": "uv",
      "args": ["tool", "run", "orchestra_server"],
      "env": {
        "API_KEY": "${EUNOMIA_API_KEY}",
        "REQUEST_TIMEOUT": "30"
      }
    }
  }
}

Replace ${EUNOMIA_API_KEY} with your environment variable.

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:

{
  "eunomia-mcp-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 “eunomia-mcp-server” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Between the two tables, this MCP provides a basic but important data governance orchestration layer for LLM applications, but lacks detailed documentation on prompts, resources, and tools. Given its deprecation notice and limited explicit features, the score is moderate for production use.

MCP Score