InnerVault

Library

85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

  1. RAGScore

    MCP servers

    Generate QA datasets & evaluate RAG systems with failure diagnosis. Any LLM.

    Stale Official MCP Registry, io.github.HZYAI Updated 6 months ago 2 notes

    ragscore@0.8.6
  2. Bulwark

    MCP servers

    AI agent governance: content scanning, audit logs, policy evaluation, session management.

    Stale Official MCP Registry, io.github.bpolania Updated 8 months ago 2 notes

    ghcr.io/bpolania/bulwark:v0.2.0
  3. Calc Eval

    MCP servers

    Evaluate a+b style arithmetic. Expression discarded.

    Stale Official MCP Registry, io.github.sadri-dridi Updated 2 months ago 1 note

  4. surfbird-mcp

    MCP servers

    Self-hosted Kitesurf headless browser: markdown, screenshots, PDF, evaluate, batch.

    Stale Official MCP Registry, io.github.terry2010 Updated 2 days ago 2 notes

    surfbird-mcp@0.1.2
  5. samyama-graph

    MCP servers

    Rust graph-vector database: OpenCypher (99.9% of evaluated TCK scenarios pass), vector search, graph algorithms, RESP + HTTP. LDBC SNB Interactive and BI complete; 1B edges on one machine.

    Stale GitHub, samyama-ai 185 ★Apache-2.0Updated 8 days ago

    git clone https://github.com/samyama-ai/samyama-graph.git
  6. Mini Program Engineering Skill Suite is an Agent Skill suite for evidence‑first mini‑program development. It helps agents bring WeChat or other mini‑program projects from vague intent to reliable engineering work: project intake, product specification, architecture, implementation, UI & device adaptation, debugging, verification, release readiness.

    Stale GitHub, NocodeMrLi 95 ★MITUpdated 13 days ago

    git clone https://github.com/NocodeMrLi/mini-program-engineering-skill-suite.git
  7. Make AI agents aim higher without losing control: a Claude Code skill with two bars per task, a cheap gate check before expensive work, and an independent verifier that never sees the worker's reasoning. Plain markdown, EN + RU.

    Stale GitHub, alexpiar 23 ★MITUpdated 22 days ago

    git clone https://github.com/alexpiar/be-ambitious-harness.git
  8. PromptOT

    MCP servers

    Manage, version, and publish LLM prompts with blocks, variables, and evaluations.

    Stale Official MCP Registry, com.promptot Updated 7 months ago 3 notes

    @prompt-ot/mcp@0.1.2
  9. RUNaDIVA

    MCP servers

    Autonomous Decision Intelligence for evaluating economic decisions before value is committed.

    Stale Official MCP Registry, com.runadiva Updated 50 days ago 1 note

  10. AgentPing

    MCP servers

    Production observability for AI agents: search runs, read evaluations, acknowledge incidents.

    Stale Official MCP Registry, io.agentping Updated 2 months ago 1 note

  11. BIGHUB

    MCP servers

    Decision learning for AI agent actions. Evaluate, score, decide, and learn from outcomes.

    Stale Official MCP Registry, io.bighub Updated 7 months ago 2 notes

    @bighub/bighub-mcp@0.2.1
  12. CreditRisk Oracle

    MCP servers

    B2B credit risk evaluator and supply chain health scoring oracle.

    Stale Official MCP Registry, io.github.Evozim Updated 5 months ago 1 note

  13. PromptBranch

    MCP servers

    Local-first MCP server for versioning, searching, evaluating, and improving AI prompts.

    Stale Official MCP Registry, io.github.PromptBranch Updated 2 months ago 1 note

    @promptbranch/mcp@0.2.6
  14. Company-scoped accounting reads, writes and workflows. Supervised synthetic evaluation only.

    Stale Official MCP Registry, io.github.andrewblount Updated 2 months ago 1 note

    https://github.com/andrewblount/polyaccounts-agent-kit/releases/download/v1.0.2/polyaccounts-hosted.mcpb@1.0.2
  15. mcp-prowl

    MCP servers

    Discover, evaluate, and compare SaaS APIs. Agent-verified scores and metrics.

    Stale Official MCP Registry, io.github.opcastil11 Updated 8 months ago 2 notes

    mcp-prowl@0.1.1
  16. Ask Jev

    MCP servers

    Evaluate state with typed choice, score, and probability questions.

    Stale Official MCP Registry, io.github.pollinations Updated 14 days ago 1 note

  17. Apricot

    MCP servers

    Manage SysML2 projects; check, evaluate, verify, query, document and diagram models.

    Stale Official MCP Registry, tools.apricot Updated 32 days ago 1 note

  18. PayStage Preflight

    MCP servers

    Evaluate x402 PaymentRequired against a local spending policy before an agent pays

    Stale Official MCP Registry, xyz.paystage Updated 6 days ago 1 note

    @paystage/preflight@0.2.2
  19. headlessstage

    MCP servers

    Browser automation: navigate, click, fill, screenshot and evaluate in a headless browser.

    Stale Official MCP Registry, io.github.CloudCorpRecords Updated 16 days ago 1 note

    @reneturcios/headlessstage@0.1.0
  20. Host-neutral agent skills for Cursor, Copilot, Codex, and Claude Code, each linted, evaluated, security-scanned, and install-verified before release.

    Stale GitHub, renzrollon 7 ★MITUpdated 25 days ago

    git clone https://github.com/renzrollon/shippable-skills.git
  21. Claude skills that turn Dubai / UAE property deals into client-ready evaluation reports — real market data, clear verdicts, every calculation shown.

    Stale GitHub, AbdullaAlzarooni 29 ★Custom licence (see repository)Updated 28 days ago

    git clone https://github.com/AbdullaAlzarooni/ultimate-real-estate-calculator.git
  22. jev-mode

    Skills

    Claude Code/Codex skills, evals, harnesses/context tools, and learning resources that make it easy to build with Jev, TypeSafe's System One model. All materials pull directly from their canonical cookbooks and documentation.

    Stale GitHub, tiffygk 15 ★Custom licence (see repository)Updated 10 days ago

    git clone https://github.com/tiffygk/jev-mode.git
  23. archboard

    Skills

    Plan the next change with your agent on a map of the system, before it writes a line. Then follow any feature into the code, and see every place where the map and the code disagree.

    Indexed GitHub, miklschmidt 11 ★Custom licence (see repository)Updated yesterday

    git clone https://github.com/miklschmidt/archboard.git
  24. RPN Calculator

    MCP servers

    Evaluates Reverse Polish Notation (postfix) expressions: arithmetic, trig, logs, bitwise ops.

    Stale Official MCP Registry, com.apished Updated 3 months 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.