- Conduid
- Marketplace
- #agent-evaluation
MCP servers tagged agent-evaluation
82 live MCP servers tagged "agent-evaluation", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with agent-evaluation.
Tracebench
RCAgentBench: a benchmark measuring how tool design and agent instructions affect LLM agents doing root cause analysis on distributed traces.
Oh No My Claudecode
The coding harness that measures itself. Wraps Claude Code / Codex / OpenCode, blocks false "done" with an independent verifier, mediates side effects, writes tamper-evident recei…
Financial Advisor Agent
Multi-agent financial AI system that analyzes stocks, alternative investments, and human capital ROI using Google ADK and Gemini.
Labgo
Change Impact Analyst: code graph, git ground truth, hybrid retrieval, and an honestly measured agent
Sentinel Engine Crewai
A hierarchical CrewAI crew that watches a Dagster → dbt → DuckDB pipeline, diagnoses 14 injected failure modes, and is scored against a ground-truth ledger.
Rtrace Agent Reliability
R-TRACE: Stateful agent evaluation and release reliability with reproducible Windows GPU evidence.
Aobench
Role-aware, permission-enforced benchmark for LLM agents that operate HPC systems — SLURM, telemetry, RBAC, docs, facility. A policy violation hard-fails the task. 88 tasks (10 ca…
Verifyax Plugins
Claude Code plugin marketplace for VerifyAX — agent evaluation, functional and non-functional verification from Conscium
Craftonomous
Craftonomous is an agent-agnostic Minecraft embodiment and evaluation substrate: an MCP-native body with a declared perception budget and reliability-tracked skills.
Agent Invariants
Deterministic behavior contracts for AI agents — preserve approvals, stop semantics, tool scope, recovery, and proof before done.
Testgen Eval
An agent-eval harness that gates and judges testgen's generated test suites via MCP — deterministic checks plus an LLM-judge scorecard.
Apollo Project
A locally-running evaluation environment that simulates knowledge-work tools (like Slack and task managers) to rigorously test and audit AI agents on complex, multi-step tasks.
Tracefact
Evidence-first reliability reports and reproducible replay for coding and browser agents.
Judgment Labs
Judgment Labs — independent third-party profile of a public API surface, by API Evangelist. Judgment Labs builds the continuous-improvement stack for AI agents: tooling to trace,…
Agentrig
Evidence-first regression testing for AI agents: turn production traces into reviewed, replayable cases that gate releases.
Energyevals
AI agent evaluation framework for energy analytics — multi-provider LLMs, benchmark runner, MCP-based tool ecosystem.
Windtunnel
Unittest for tool-using LLM agents: reproducible scenarios scoring outcome, trajectory, constraints, and robustness.
Datalox Gated Runtime
Stateful, resettable, verifiable API worlds for tool-using agents.
Effect Witness
Dual-view evidence for declared agent-tool effect contracts under ambiguous failures.
Jovanipink Adk
Secure Google ADK runtime infrastructure for reviewed, non-executable Agent Skill bundles.
Verifyax Agent Integrations
Use VerifyAX — the agent evaluation and verification platform from Conscium — from OpenAI and Google Gemini. Includes a synced mirror of the Gateway public OpenAPI spec, a Custom…
Dayquest Agent
Evidence-first MCP timeline debugger with reversible provenance replay, Supported/Unknown/Conflict states, and auditable intervention receipts.
Enterprise Agent Reliability Lab
A production-oriented enterprise AI agent with MCP tools, Agent Skills, tracing, reliability controls, and reproducible evaluations.
Outputproof
Verification infrastructure for AI agent output — assertions, LLM-as-judge scoring, audit logs, and reliability gates before generated work is trusted.
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.
Lightweight Coding Agent Harness
A lightweight, independently implemented Agent Runtime for structured tool calling, context management, recovery, Skills, MCP and agent evaluation.
Secondstrike Agents
Put your AI agent in command of a nation in a real-time world war on a 3D globe. MCP server, starter bots and an LLM agent for any model.
Verifyax Plugins Claude
Claude Code plugin marketplace for VerifyAX — agent evaluation, functional and non-functional verification from Conscium
Eval
CI-embeddable eval harness for MCP agents — scores the sequence of tool calls your agent makes, not just text output
Claude Eval Harness
Regression-diff eval harness for Anthropic tool-use agents that surfaces LLM-judge reasoning drift, not just pass/fail flips
Intelligent Voice Driving System
Monitor driver safety and control in-vehicle systems using computer vision, real-time behavior tracking, and a local Qwen-7B language model.
Kinesift Public
Observe AI agents from outside the sandbox: tamper-evident side-effect logs for Docker-run agents, with Harbor import and reset-able task environments.