Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
DiscoverIA
MCP serversRead-only registry of AI-assisted scientific claims and where their evaluation stands (fr/en)
-
poker-mcp
MCP serversEvaluate poker hands, compare players and pick the best five from seven cards - fully local.
@mrfentmen/poker-mcp@1.0.1 -
OpenWater MCP by usefulapi
MCP serversList programs, applications, evaluations and sessions; create and update users in OpenWater.
-
MCP Yellow Pages
MCP serversFind and evaluate MCP servers: search the independent MCP Yellow Pages directory.
-
EvalGate
MCP serversRun AI evaluations, record agent traces and gate releases on evidence, with scoped org access.
-
LLM Prover
MCP serversLLM evaluation: compare models on cost and quality, score outputs, run benchmarks, analyse agents.
-
DeepResearch-Bench-II
Datasets & benchmarksDeepResearch Bench II (DRB2) is the follow-up to DeepResearch Bench, with a stronger focus on measuring the gap between deep research systems and human experts. It does so by decomposing expert-written reports into hierarchical rubrics covering presentation, analysis, and evidence, and using them to evaluate model-generated.
git clone https://github.com/imlrz/DeepResearch-Bench-II.git -
OntoRamp Decision Intelligence
MCP serversLog, evaluate, and ground AI decisions against authority context. Returns PASS, WARN, or BLOCK.
-
WebMCP Eval
MCP serversEvaluate one public URL for WebMCP readiness: intent, tools observed, recommended, do-not-expose.
-
Judges Panel
MCP servers45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
@kevinrabun/judges@3.129.9 -
AuctionTrace
MCP serversHistorical ES Book Pressure data, matched evidence, and evaluation guidance for $5 USDC via x402.
-
Agentic Platform
MCP serversFree MCP tools: the only MCP linter, health checks, cost estimation, and trust evaluation.
-
Facet
MCP serversFacet's agent builds, evaluates, serves and maintains a small model for one repeated task.
-
IoMarkets.ai guide
MCP serversGuide to IoMarkets.ai Federated Computing: receipt checks, runs, costs and evaluation requests.
-
ML Referee
MCP serversEvaluate ML features beyond a baseline and test bounded feature repairs. Invite-only beta.
-
prompt-potter-optimizer
SkillsLLM-driven evolution of prompts and pipelines. Evolves the prompt and the pipeline's parameters together against your labeled data, cuts losing candidates early, and shows every measurement behind the winner. Open source.
git clone https://github.com/PromptPotter/prompt-potter-optimizer.git -
deskcert
MCP serversEvaluates whether an AI agent is safe to operate internal web apps via an MCP run_suite tool.
deskcert-cli@0.1.5 -
shield-kya
MCP serversStops your coding agent from deleting, leaking or dropping things. MCP gate: evaluate and ingest.
@shield-agent/kya@0.35.5 -
mcp-opa-authz
MCP serversAuthorization answers from real policy code: evaluate Rego locally, or ask an AuthZEN 1.0 PDP.
ghcr.io/kanywst/mcp-opa-authz:0.6.2 -
github-audit-mcp
MCP serversEvaluates any GitHub repository for license risk, maintenance velocity, stars/forks, and security.
-
케어그레이드 — 장기요양기관 평가 조회
MCP serversKorean long-term care institutions: NHIS evaluation grade, year, address, staffing, with page URLs.
-
Did It Work?
MCP serversCharity evidence for AI agents: cited evaluator figures, caveats and an outcome ledger. Read-only.
-
Levels.fyi
MCP serversSalary, level and job data from 1M+ pay reports. Benchmark pay, evaluate offers, search open jobs.
-
LotAi
MCP serversTerrains du Québec : évaluation, zonage, zones inondables, CPTAQ et taxes pour 4,4 M de lots.
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.