Skip to main content
Glama

Root Signals MCP Server

Official
by root-signals
tools.py2.54 kB
"""Tool catalogue for the RootSignals MCP server.""" from __future__ import annotations from mcp.types import Tool from root_signals_mcp.schema import ( CodingPolicyAdherenceEvaluationRequest, EvaluationRequest, EvaluationRequestByName, ListEvaluatorsRequest, ListJudgesRequest, RunJudgeRequest, ) def get_tools() -> list[Tool]: """Return the list of MCP *tools* supported by RootSignals.""" return [ Tool( name="list_evaluators", description="List all available evaluators from RootSignals", inputSchema=ListEvaluatorsRequest.model_json_schema(), ), Tool( name="run_evaluation", description="Run a standard evaluation using a RootSignals evaluator by ID", inputSchema=EvaluationRequest.model_json_schema(), ), Tool( name="run_evaluation_by_name", description="Run a standard evaluation using a RootSignals evaluator by name", inputSchema=EvaluationRequestByName.model_json_schema(), ), Tool( name="run_coding_policy_adherence", description="Evaluate code against repository coding policy documents using a dedicated RootSignals evaluator", inputSchema=CodingPolicyAdherenceEvaluationRequest.model_json_schema(), ), Tool( name="list_judges", description="List all available judges from RootSignals. Judge is a collection of evaluators forming LLM-as-a-judge.", inputSchema=ListJudgesRequest.model_json_schema(), ), Tool( name="run_judge", description="Run a judge using a RootSignals judge by ID", inputSchema=RunJudgeRequest.model_json_schema(), ), ] def get_request_model(tool_name: str) -> type | None: """Return the Pydantic *request* model class for a given tool. This is useful for validating the *arguments* dict passed to MCP-`call_tool` before dispatching. Returns ``None`` if the name is unknown; caller can then fall back to a generic model or raise. """ mapping: dict[str, type] = { "list_evaluators": ListEvaluatorsRequest, "list_judges": ListJudgesRequest, "run_coding_policy_adherence": CodingPolicyAdherenceEvaluationRequest, "run_evaluation_by_name": EvaluationRequestByName, "run_evaluation": EvaluationRequest, "run_judge": RunJudgeRequest, } return mapping.get(tool_name)

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/root-signals/root-signals-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server