- Conduid
- Marketplace
- #evals
MCP servers tagged evals
128 live MCP servers tagged "evals", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with evals.
Agentops Watchtower
Local-first AgentOps flight recorder and capability firewall for MCP-based coding agents with OpenTelemetry traces.
Trade Gate
Order-validation gates for an automated trader — a stale book refuses everything
Prompt Lab
Prompt evaluation workbench as an MCP server — run evals, compare providers, and test assertions directly from Claude Code or any MCP host.
Pagelens
MCP server that audits how legible a web page is to AI agents, with evidence-grounded findings and evals
Agent Finops Sandbox
An evaluation infrastructure layer for autonomous coding agents. Measure true FinOps costs, cache economics, and risk-aware routing for Claude Code.
Learn MCP Agent Ledger
Project #5 in a learn-MCP series: sampling, where the server borrows the host model instead of holding its own key. Adds a cost ledger, spend gates, and replayable runs so every m…
AI Transformation 90
A transformation copilot for the first 90 days of an AI program — playbook, opportunity portfolio, costed business cases, operating model, plus the software to run it: MCP assista…
AI Playbook
Curated collection of LLM and agent artifacts: prompts, agents, skills, MCP servers, and evals.
Procurement Agent Evals
A bid/no-bid procurement agent for federal solicitations with a functional eval harness
Windtunnel
Unittest for tool-using LLM agents: reproducible scenarios scoring outcome, trajectory, constraints, and robustness.
Agent Eval Gate
MCP eval-gate server: an agent's only path to moving money runs a fail-closed, version-pinned OFAC screen-before-transfer control first. Stdlib-only, zero-install, polarity-proven.
Nivara AI
The AI support layer for Nivara Desk: answers what it can safely answer, asks when a request is ambiguous, and escalates the rest to a human. Python, FastAPI and Qdrant, with hybr…
Simple Project Tool
API-first project tracker (projects → stories → tasks) with scoped API keys for AI agents. FastAPI, async SQLAlchemy, PostgreSQL, React 19 and a Typer CLI.
Ops Triage Agent
Enterprise agentic IT/Ops support triage: a multi-step LLM agent with an MCP server, RBAC + human-approval gates, hash-chained audit, RAG with data governance, and an eval-gated C…
Mainsheet
An agents runtime. Define an agent in one file, run it governed, prove what it did. A policy gate decides before every tool call in code the model never sees; budgets cap cost and…
Aca AI Orchestrator
Orquestador multiagente (TypeScript/pnpm) que genera diagnósticos de presencia digital y propuestas comerciales para negocios locales de Acámbaro, Gto. — Claude API + MCP.
Guarded Infra MCP
Read-only Kubernetes and AWS access for AI agents, behind a deny-by-default policy gate with a JSONL audit trail and eval suites that score both per-call block rate and whole-traj…
Context API
Memory and brand-context layer for AI agent systems. Multi-tenant MCP server — 39 tools auto-generated from a live OpenAPI spec. PostgreSQL, per-workspace isolation, scored eval h…
Agents AI
Agentes LangGraph com HITL via interrupt(), MCP server custom e evals LLM-as-judge — multi-provider (Claude, OpenAI, Ollama)
Claude Triage
PII-safe, audit-logged triage agent — a minimal Forward-Deployed reference for Claude tool-use + evals. Live demo at claude-triage.vercel.app
Learn MCP Agent Guard
An MCP host that stops and asks before it does anything it can't undo: Postgres persistence, human-in-the-loop approval gates, evals, and replay.
Agent Proof Kit
Deterministic proof gates and a raw-byte write firewall for AI agents — CLI, MCP, in-toto receipts, Codex CLI and Mistral Vibe.
Snapgauge
Contract tests for MCP servers: snapshot schema and behavior, then fail CI when the next version moves.
F1 Telemetry MCP
MCP server exposing live F1 game UDP telemetry to LLM agents, with evals (TypeScript)
Readonly SQL MCP
An MCP server that gives an AI agent read-only SQL access: three independent locks, each proven by breaking it on purpose, plus agent evaluations.
Evals
A deadly simple evaluation framework for AI models
Retention Agent
An AI agent that tells your team what to do next for every customer, cites the events behind it, and gets graded by an eval harness.
Agentflight
Write LLM agents in plain Python: watch every call live, step in, replay any step, and test them with evals. Panel for the browser, VS Code, Cursor and JetBrains.