Root Signals MCP Server

Equip AI agents with evaluation and self-improvement capabilities with Root Signals.

Remote serverstreamable-httpPython

What is the Root Signals MCP server?

Root Signals becomes available to MCP clients through the root signals mcp server. Equip AI agents with evaluation and self-improvement capabilities with Root Signals.

What Root Signals does

Measurement & Control for LLM Automations

This project serves as a bridge between Scorable API and MCP client applications, allowing AI assistants and agents to evaluate responses against various quality criteria.

Key capabilities

  • Exposes Scorable evaluators as MCP tools
  • Implements SSE for network deployment
  • Compatible with various MCP clients such as Cursor

Tools it exposes

Once connected, the assistant can call these 2 tools directly:

  • Synposis — Description
  • Impacts — Severity rating (low, medium or high)

Installing the root signals mcp server

The server is distributed via a container image as ghcr.io/scorable/scorable-mcp, so most clients can run it without a manual build step. Add it to your MCP client's configuration and restart the client to pick it up — the copy-paste configs for Claude Desktop, Claude Code and Cursor are on this page.

Configuration

Before the server will start you need to supply one environment variable: SCORABLE_API_KEY. Keep credentials in your client's env block or a secrets manager rather than committing them.

Where it fits

Developer-tool servers are usually the first ones people connect, because they turn "help me with this code" into an assistant that can actually read the repo and act on it. Root Signals sits in that group, and the shape of its toolset — Synposis, Impacts — tells you what it is really for. Worth comparing against the other developer tools servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.

Practical notes

  • This is a hosted server — you point your client at an endpoint rather than running a local process, so there is nothing to keep updated on your machine.
  • It will not start until its required credentials are present, so set those before wondering why the tools never appear.
  • Written in Python.
  • MCP clients ask for confirmation before each tool call by default. Keep that on while you learn what the root signals mcp server actually does with your data.
  • Every entry in this directory is reviewed by hand before it goes live, and details are checked against the project's own documentation.

Available tools

ToolWhat it does
SynposisDescription
ImpactsSeverity rating (low, medium or high)

How to install the Root Signals MCP server

{
  "mcpServers": {
    "root-signals": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "ghcr.io/scorable/scorable-mcp"],
      "env": {
        "SCORABLE_API_KEY": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
SCORABLE_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Root Signals to Synposis.
  • Use Root Signals to Impacts.

Frequently asked questions

It connects Root Signals to MCP-compatible AI assistants such as Claude and Cursor, exposing 2 tools (Synposis, Impacts) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Root Signals directly.