Evaluation & Benchmarks

Official Model Context Protocol (MCP) server for JevGuard deterministic evaluation runtime.

MCP Server for querying enterprise performance benchmark values (企业绩效标准值查询服务)

MCP server for the Codabench REST API — drives a full ML-benchmark participant workflow.

CleanLibrary MCP server — exposes verdict-aware supply-chain risk assessment as Model Context Protocol tools for AI agent workflows

Canvas LMS for instructors over MCP — build pages and quizzes, and grade

Judges agent/RAG outputs (relevance, hallucination, accuracy, routing, prompt injection) using Laya instead of LLM-as-judge -- usable as an MCP server or as a plain Python library.

Reviews, 14 bounded tax and super worksheets, cited retrieval from your local Markdown. Not advice.

Methodology-driven MCP server for revenue intelligence: RFM analysis, 14.5-point ICP scoring, pipeline health scoring, and HubSpot integration

Revenue intelligence MCP: RFM analysis, 14.5-point ICP scoring, pipeline health. HubSpot.

Alpha Terminal MCP Server - the governance layer for the AI economy

AGM — Agent Memory Management. Provenance-tagged memory infrastructure for multi-agent AI systems. MCP server with trust scoring, behavioral fingerprinting, and memory poisoning defense.

MCP server for autonomous AI agent trust — cryptographic provenance (Chain of Consciousness with Bitcoin OpenTimestamps), decentralized reputation (Agent Rating Protocol with bilateral blind evaluation). Part of the 7-protocol Agent Trust Stack.

MCP Server for Agent Reputation & Trust Scoring

Deterministic evaluation tools for AI coding agents, exposed as an MCP server.

Query OpenTelemetry traces from agent runs through MCP.

MCP server wrapping the Artificial Analysis API for LLM and multimodal model data queries

MCP server for automatic assessment (grading) of tasks.

custovox.ai support ticket scoring MCP server: priority, category, sentiment, escalation risk

Local emulator for Slack, Gmail, Drive, GitHub, Jira, Notion, S3 and more, with per-document ACLs

Query pre-computed SQL engine benchmarks. Runs standalone, no server setup required.