Root Signals Evaluators MCP server for AI agents

The Root Signals MCP Server provides a bridge between the Root Signals API and Model Context Protocol (MCP) client applications, allowing AI assistants and agents to evaluate responses against various quality criteria.

Installation

Prerequisites

You'll need:

A Root Signals API key (get one by signing up or generating a temporary key)
Docker (for the recommended installation method) or a system with Python

Installing with Docker (Recommended)

Run the MCP server using Docker with the SSE transport:

docker run -e ROOT_SIGNALS_API_KEY=<your_key> -p 0.0.0.0:9090:9090 --name=rs-mcp -d ghcr.io/root-signals/root-signals-mcp:latest

You should see logs confirming the server is running:

docker logs rs-mcp
2025-03-25 12:03:24,167 - root_mcp_server.sse - INFO - Starting RootSignals MCP Server v0.1.0
2025-03-25 12:03:24,167 - root_mcp_server.sse - INFO - Environment: development
2025-03-25 12:03:24,167 - root_mcp_server.sse - INFO - Transport: stdio
2025-03-25 12:03:24,167 - root_mcp_server.sse - INFO - Host: 0.0.0.0, Port: 9090
2025-03-25 12:03:24,168 - root_mcp_server.sse - INFO - Initializing MCP server...
2025-03-25 12:03:24,168 - root_mcp_server - INFO - Fetching evaluators from RootSignals API...
2025-03-25 12:03:25,627 - root_mcp_server - INFO - Retrieved 100 evaluators from RootSignals API
2025-03-25 12:03:25,627 - root_mcp_server.sse - INFO - MCP server initialized successfully
2025-03-25 12:03:25,628 - root_mcp_server.sse - INFO - SSE server listening on http://0.0.0.0:9090/sse

Installing with stdio

For clients like Cursor or Claude Desktop, you can set up the server using stdio:

{
    "mcpServers": {
        "root-signals": {
            "command": "uvx",
            "args": ["--from", "git+https://github.com/root-signals/root-signals-mcp.git", "stdio"],
            "env": {
                "ROOT_SIGNALS_API_KEY": "<myAPIKey>"
            }
        }
    }
}

Client Configuration

Configuring MCP Clients

For clients that support SSE transport, add the server to your configuration. For example, in Cursor:

{
    "mcpServers": {
        "root-signals": {
            "url": "http://localhost:9090/sse"
        }
    }
}

Usage Examples

Evaluating and Improving AI Responses

You can instruct an AI agent to evaluate its own responses using Root Signals evaluators:

Ask for an explanation of some code
The agent can discover appropriate evaluators (like "Conciseness" and "Relevance")
Execute these evaluators against its response
Provide an improved explanation based on the feedback
Re-evaluate the improved response to confirm higher quality

Using the MCP Reference Client

You can use the provided Python client directly in your code:

from root_mcp_server.client import RootSignalsMCPClient

async def main():
    mcp_client = RootSignalsMCPClient()
    
    try:
        await mcp_client.connect()
        
        evaluators = await mcp_client.list_evaluators()
        print(f"Found {len(evaluators)} evaluators")
        
        result = await mcp_client.run_evaluation(
            evaluator_id="eval-123456789",
            request="What is the capital of France?",
            response="The capital of France is Paris."
        )
        print(f"Evaluation score: {result['score']}")
        
        result = await mcp_client.run_evaluation_by_name(
            evaluator_name="Clarity",
            request="What is the capital of France?",
            response="The capital of France is Paris."
        )
        print(f"Evaluation by name score: {result['score']}")
        
    finally:
        await mcp_client.disconnect()

Measuring Prompt Template Quality

You can evaluate your prompt templates by asking an agent (like Cursor) to evaluate them:

Evaluate the summarizer prompt in terms of clarity and precision. use Root Signals

The agent will use Root Signals evaluators to score your prompt and provide improvement suggestions.

Available Tools

The server exposes these tools:

list_evaluators - Lists all available evaluators on your Root Signals account
run_evaluation - Runs a standard evaluation using a specified evaluator ID
run_evaluation_by_name - Runs a standard evaluation using a specified evaluator name
run_coding_policy_adherence - Runs a coding policy adherence evaluation using policy documents
list_judges - Lists all available judges on your Root Signals account
run_judge - Runs a judge using a specified judge ID

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "root-signals" '{"url":"http://localhost:9090/sse"}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "root-signals": {
            "url": "http://localhost:9090/sse"
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "root-signals": {
            "url": "http://localhost:9090/sse"
        }
    }
}

3. Restart Claude Desktop for the changes to take effect