Root Signals
Created 6 months ago
Root Signals MCP Server exposes evaluators for AI assistants & agents.
What is Root Signals?
Improve and quality control your outputs with evaluations using LLM-as-Judge
Documentation
Root Signals MCP Server
Overview
This project serves as a bridge between Root Signals API and MCP client applications, allowing AI assistants and agents to evaluate responses against various quality criteria.
Features
- Exposes Root Signals evaluators as MCP tools
- Implements SSE for network deployment
- Compatible with various MCP clients such as Cursor
Tools
The server exposes the following tools:
list_evaluators- Lists all available evaluators on your Root Signals accountrun_evaluation- Runs a standard evaluation using a specified evaluator IDrun_evaluation_by_name- Runs a standard evaluation using a specified evaluator namerun_coding_policy_adherence- Runs a coding policy adherence evaluation using policy documents such as AI rules fileslist_judges- Lists all available judges on your Root Signals account.run_judge- Runs a judge using a specified judge ID
How to use this server## 1. Get Your API Key
Sign up & create a key or generate a temporary key
2. Run the MCP Server## 3. with sse transport on docker (recommended)
docker run -e ROOT_SIGNALS_API_KEY= -p 0.0.0.0:9090:9090 --name=rs-mcp -d ghcr.io/root-signals/root-signals-mcp:latest
You should see some logs (note: /mcp is the new preferred endpoint; /sse is still available for backward‑compatibility)
4. with stdio from your MCP host Usage Examples
- Evaluate and improve Cursor Agent explanations
- Use the MCP reference client directly from code
- Measure your prompt templates in Cursor
How to Contribute
Contributions are welcome as long as they are applicable to all users.
Limitations
Network Resilience Current implementation does not include backoff and retry mechanisms for API calls.
Server Config
{
"mcpServers": {
"root-signals-server": {
"command": "npx",
"args": [
"root-signals"
]
}
}
}