InnerVault

Library

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

Results

  1. agent-eval

    MCP servers

    Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.

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

    agent-regress-cli@0.1.8
  2. Converra

    MCP servers

    Fix production agent behavior with tested changes and a production verdict on every fix.

    Stale Official MCP Registry, io.github.converra Updated 33 days ago 1 note

  3. MCP Safety Warden

    MCP servers

    MCP proxy adding security scanning, behavioral profiling, risk gating, and safe tool call execution.

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

    mcpsafetywarden@1.7.6
  4. Behavioral health NPIs newly pending Medicare provider enrollment; free validated preview.

    Stale Official MCP Registry, io.github.unitedideas Updated 4 months ago 2 notes

  5. corpus

    MCP servers

    Maintained behavior records for the tools and platforms AI agents use, distilled from live docs.

    Stale Official MCP Registry, co.tasklinkr Updated 28 days ago 1 note

  6. Microsoft Clarity MCP

    MCP servers

    Microsoft Clarity MCP: behavioral UX analytics, rage clicks, dead clicks, scroll, and JS errors.

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

    microsoft-clarity-mcp@0.1.3
  7. super-ux

    Skills

    Define product behavior, trace UX scenarios and keep copy consistent through brand voice, audits and code checks.

    Stale GitHub, ssheleg 6 ★MITUpdated 22 days ago

    git clone https://github.com/ssheleg/super-ux.git
  8. BenchGecko

    MCP servers

    AI model prices per provider, benchmarks, own AI behavior tests and AI economy data, with sources.

    Stale Official MCP Registry, ai.benchgecko Updated 42 days ago 1 note

  9. County and tract-level health outcomes, behaviors, and preventive services from CDC PLACES

    Stale Official MCP Registry, com.olyport Updated 7 months ago 1 note

  10. cdc-health-mcp-server

    MCP servers

    Search and query CDC public health data — mortality, vaccinations, surveillance, behavioral risk.

    Stale Official MCP Registry, io.github.cyanheads Updated 15 days ago 2 notes

    @cyanheads/cdc-health-mcp-server@0.11.0
  11. Commerce Intelligence

    MCP servers

    Behavioral-science tools for commerce: checkout, drop-off, pricing, churn. 5 free calls, then paid.

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

  12. Mirror

    MCP servers

    Give Claude an honest self-model — behavioral tendencies built from evidence, not session memory. Mi

    Stale Official MCP Registry, io.github.mctx-ai Updated 6 months ago 1 note

  13. Compare the values and behaviors of ${group_a} and ${group_b} in online spaces.

    Indexed prompts.chat (CC0 prompt collection), etnologiaus2022@gmail.com CC0-1.0

  14. Create real-time AI voice roleplay simulations and behavioral assessments on Atlas Primer.

    Stale Official MCP Registry, io.github.AtlasPrimer Updated 13 days ago 2 notes

    @atlasprimer/mcp-server@1.0.2
  15. Build evals from traces, code, and coding sessions, then measure and improve AI agent behavior, including your coding agents

    Indexed GitHub, relai-ai 14 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/relai-ai/agent-eval-loop.git
  16. meridian

    Tools & apps

    Zero-config Claude Code setup with enforced task scaffolding, structured memory, persistent context after compaction, plug-in code standards, optional TDD mode, and zero behavior changes for developers.

    Stale GitHub, markmdev 189 ★Updated 8 months ago

    git clone https://github.com/markmdev/meridian.git
  17. mcp-as-a-judge

    MCP servers

    MCP as a Judge: a behavioral MCP that strengthens AI coding assistants via explicit LLM evaluations

    Stale Official MCP Registry, io.github.OtherVibes Updated 14 months ago 1 note

    mcp-as-a-judge@0.3.20
  18. XRPL wallet risk scoring. Behavioral tags, sub-scores, graph analysis. Pay per call in XRP.

    Stale Official MCP Registry, io.github.kynto2001-ctrl Updated 6 months ago 1 note

    @xrplriskscore/mcp@1.3.0
  19. litmus

    MCP servers

    Grade MCP servers A to F with the open behavioral litmus. npm: full toolset; hosted: lookups only.

    Stale Official MCP Registry, io.github.polygraphso Updated 3 months ago 2 notes

    @polygraphso/litmus@0.36.0
  20. Persistent conversational memory, behavioral code search, and bug localization for AI agents.

    Indexed Official MCP Registry, io.github.slashml-ai Updated 2 days ago 2 notes

    @slashml/mcp@1.0.14
  21. Amazon DevOps Guru

    Public APIs

    Amazon DevOps Guru is a fully managed service that helps you identify anomalous behavior in business critical operational applications. You specify the Amazon Web Services resources that you want DevOps Guru to cover, then the Amazon CloudWatch metrics and Amazon Web Services CloudTrail events related to those resources are analyzed. When anomalous behavior is detected, DevOps Guru creates an…

    Indexed APIs.guru OpenAPI Directory, Mike Ralphson Updated 5 years ago

  22. Streamline your workflow with Felix. Integrate it into your workspace and tailor its behavior to y…

    Stale Official MCP Registry, ai.smithery Updated 13 months ago 1 note

  23. Supply chain risk scoring for npm, PyPI, Cargo, and Go. 9 tools. Behavioral signals.

    Stale Official MCP Registry, io.github.piiiico Updated 4 months ago 2 notes

    proof-of-commitment@1.36.0
  24. VAIL Agent Assurance

    MCP servers

    Scan an AI agent's instructions and tools for behavior risks and generate probes that test them.

    Indexed Official MCP Registry, com.projectvail Updated 2 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.