InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. DiscoverIA

    MCP servers

    Read-only registry of AI-assisted scientific claims and where their evaluation stands (fr/en)

    Stale Official MCP Registry, ai.discoveria Updated 25 days ago 1 note

  2. poker-mcp

    MCP servers

    Evaluate poker hands, compare players and pick the best five from seven cards - fully local.

    Stale Official MCP Registry, io.github.mrfentmen Updated 8 days ago 1 note

    @mrfentmen/poker-mcp@1.0.1
  3. List programs, applications, evaluations and sessions; create and update users in OpenWater.

    Stale Official MCP Registry, io.usefulapi Updated 2 days ago 1 note

  4. MCP Yellow Pages

    MCP servers

    Find and evaluate MCP servers: search the independent MCP Yellow Pages directory.

    Stale Official MCP Registry, io.github.MCPYellowPages Updated 12 days ago 1 note

  5. EvalGate

    MCP servers

    Run AI evaluations, record agent traces and gate releases on evidence, with scoped org access.

    Stale Official MCP Registry, com.evalgate Updated 11 days ago 1 note

  6. LLM Prover

    MCP servers

    LLM evaluation: compare models on cost and quality, score outputs, run benchmarks, analyse agents.

    Stale Official MCP Registry, com.pysolvr Updated 4 days ago 1 note

  7. DeepResearch-Bench-II

    Datasets & benchmarks

    DeepResearch 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.

    Stale GitHub, imlrz 96 ★Apache-2.0Updated 28 days ago

    git clone https://github.com/imlrz/DeepResearch-Bench-II.git
  8. Log, evaluate, and ground AI decisions against authority context. Returns PASS, WARN, or BLOCK.

    Stale Official MCP Registry, com.ontoramp Updated 5 months ago 1 note

  9. WebMCP Eval

    MCP servers

    Evaluate one public URL for WebMCP readiness: intent, tools observed, recommended, do-not-expose.

    Stale Official MCP Registry, com.webmcp-eval Updated 59 days ago 1 note

  10. Judges Panel

    MCP servers

    45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.

    Stale Official MCP Registry, io.github.KevinRabun Updated 7 months ago 1 note

    @kevinrabun/judges@3.129.9
  11. AuctionTrace

    MCP servers

    Historical ES Book Pressure data, matched evidence, and evaluation guidance for $5 USDC via x402.

    Stale Official MCP Registry, io.github.VermontForest Updated 3 months ago 1 note

  12. Agentic Platform

    MCP servers

    Free MCP tools: the only MCP linter, health checks, cost estimation, and trust evaluation.

    Stale Official MCP Registry, io.github.andysalvo Updated 6 months ago 1 note

  13. Facet

    MCP servers

    Facet's agent builds, evaluates, serves and maintains a small model for one repeated task.

    Indexed Official MCP Registry, io.github.halfspacelabs Updated yesterday 1 note

  14. IoMarkets.ai guide

    MCP servers

    Guide to IoMarkets.ai Federated Computing: receipt checks, runs, costs and evaluation requests.

    Stale Official MCP Registry, io.github.SergoVashakmadze Updated 19 days ago 1 note

  15. ML Referee

    MCP servers

    Evaluate ML features beyond a baseline and test bounded feature repairs. Invite-only beta.

    Stale Official MCP Registry, io.github.scarrico Updated 21 days ago 1 note

  16. LLM-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.

    Indexed GitHub, PromptPotter 7 ★Custom licence (see repository)Updated yesterday

    git clone https://github.com/PromptPotter/prompt-potter-optimizer.git
  17. deskcert

    MCP servers

    Evaluates whether an AI agent is safe to operate internal web apps via an MCP run_suite tool.

    Stale Official MCP Registry, io.github.RudrenduPaul Updated 3 months ago 1 note

    deskcert-cli@0.1.5
  18. shield-kya

    MCP servers

    Stops your coding agent from deleting, leaking or dropping things. MCP gate: evaluate and ingest.

    Indexed Official MCP Registry, io.github.The-Pixel-Boys Updated today 2 notes

    @shield-agent/kya@0.35.5
  19. mcp-opa-authz

    MCP servers

    Authorization answers from real policy code: evaluate Rego locally, or ask an AuthZEN 1.0 PDP.

    Stale Official MCP Registry, io.github.kanywst Updated 22 days ago 2 notes

    ghcr.io/kanywst/mcp-opa-authz:0.6.2
  20. github-audit-mcp

    MCP servers

    Evaluates any GitHub repository for license risk, maintenance velocity, stars/forks, and security.

    Stale Official MCP Registry, io.github.robertoyanguas-ops Updated 34 days ago 1 note

  21. Korean long-term care institutions: NHIS evaluation grade, year, address, staffing, with page URLs.

    Stale Official MCP Registry, kr.caregrade Updated 31 days ago 1 note

  22. Did It Work?

    MCP servers

    Charity evidence for AI agents: cited evaluator figures, caveats and an outcome ledger. Read-only.

    Stale Official MCP Registry, org.diditwork Updated 22 days ago 1 note

  23. Levels.fyi

    MCP servers

    Salary, level and job data from 1M+ pay reports. Benchmark pay, evaluate offers, search open jobs.

    Stale Official MCP Registry, fyi.levels Updated 18 days ago 1 note

  24. LotAi

    MCP servers

    Terrains du Québec : évaluation, zonage, zones inondables, CPTAQ et taxes pour 4,4 M de lots.

    Stale Official MCP Registry, io.github.Nickdub82 Updated 11 days ago 1 note

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.