InnerVault

Library

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

Results

  1. Check PDFs against PDF/UA-1 with veraPDF; see which failures an automatic fix removes; explain rules

    Stale Official MCP Registry, io.github.nyo-agentti Updated 22 days ago 1 note

  2. Humanform

    MCP servers

    Anthropometric prediction API: predict measurements, list countries, list measurement names.

    Stale Official MCP Registry, app.humanform Updated 4 months ago 2 notes

    @humanform/mcp@0.1.3
  3. deepmark

    Datasets & benchmarks

    Deepmark AI enables a unique testing environment for language models (LLM) assessment on task-specific metrics and on your own data so your GenAI-powered solution has predictable and reliable performance.

    Stale GitHub, IngestAI 104 ★AGPL-3.0Updated 2 years ago

    git clone https://github.com/IngestAI/deepmark.git
  4. LLM Audit

    MCP servers

    Measure whether AI assistants actually recommend a brand, from measured answers.

    Stale Official MCP Registry, app.llmaudit Updated 2 months ago 3 notes

    llmaudit-mcp@0.1.0
  5. Asked Thrice

    MCP servers

    Measure whether AI assistants actually recommend a brand, from measured answers.

    Stale Official MCP Registry, com.askedthrice Updated 2 months ago 2 notes

    askedthrice-mcp@0.1.0
  6. council-signal-mcp

    MCP servers

    Signed AI measurement (13-axis, deterministic judge). Measurement, not certification; monitored cont

    Stale Official MCP Registry, io.github.CSOAI-ORG Updated 16 days ago 2 notes

    council-signal-mcp@0.1.3
  7. green-mcp

    MCP servers

    Measure a program's CPU energy and LLM tokens, then refactor it cheaper. Measure, never estimate.

    Stale Official MCP Registry, io.github.rlawogh1005 Updated 3 months ago 1 note

    green-mcp@0.1.2
  8. uisight

    MCP servers

    Your AI sees the screen but can't measure it — measured web UI findings, shared live sessions

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

    uisight@0.34.0
  9. Council of AI GSPC

    MCP servers

    Independent AI-governance measurement MCP. Free reads + x402 evidence. Measurement not cert.

    Stale Official MCP Registry, io.github.CSOAI-ORG Updated 16 days ago 3 notes

    csoai-gspc-mcp@0.2.2
  10. Measure how AI assistants cite your brand. Returns measured data and ready-to-apply fixes.

    Stale Official MCP Registry, app.clicon Updated 3 months ago 1 note

  11. harness-score

    Agents & frameworks

    Your AI coding agent is only as reliable as the harness around it. Measure that harness in seconds with harness-score.

    Indexed GitHub, paladini 621 ★MITUpdated 2 days ago

    git clone https://github.com/paladini/harness-score.git
  12. site

    MCP servers

    Measured Survey Cost: the site's own MCP server — enquiry (enquiry = a human handoff, not a...

    Stale Official MCP Registry, uk.co.measuredsurveycost Updated 44 days ago 1 note

  13. Proteus

    Agents & frameworks

    Self-evolution for any agent harness. Plug in. Evolve. Measure.

    Indexed GitHub, proteus-evolve 112 ★MITUpdated 2 days ago

    git clone https://github.com/proteus-evolve/Proteus.git
  14. AIRTBench-Code

    Datasets & benchmarks

    Code Repository for: AIRTBench: Measuring Autonomous AI Red Teaming Capabilities in Language Models

    Stale GitHub, dreadnode 111 ★Apache-2.0Updated 32 days ago

    git clone https://github.com/dreadnode/AIRTBench-Code.git
  15. ResearcherSkill

    Prompts

    Asks what to optimise and how to measure it, then runs experiments on its own branch.

    Stale GitHub, krzysztofdudek 269 ★MITUpdated 7 days ago

    git clone https://github.com/krzysztofdudek/ResearcherSkill.git
  16. WhatPulse

    Public APIs

    Small application that measures your keyboard/mouse usage

    Indexed public-apis (GitHub list)

  17. Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior.

    Indexed GitHub, NVIDIA 1,963 ★Apache-2.0Updated today

    git clone https://github.com/NVIDIA/SkillEvaluator.git
  18. { "role": "Practical workplace ergonomics advisor who assesses home office setups from a person's own description and measurements", "task": "Turn my description of my home office desk setup, my measurements, and any…

    Indexed prompts.chat (CC0 prompt collection), f CC0-1.0

  19. WeatherTotals

    Public APIs

    Measured US snow, rain, hail and aurora totals by state and city

    Indexed public-apis (GitHub list)

  20. A codex plugin for running optimization loops inside a codebase. It is useful when you have a measurable target and many possible changes to try: test runtime, build speed, bundle size, model loss, Lighthouse scores, memory use, query latency, or any other metric you can print from a script.

    Stale GitHub, TheGreenCedar 834 ★Apache-2.0Updated 36 days ago

    git clone https://github.com/TheGreenCedar/codex-autoresearch.git
  21. surfaces

    MCP servers

    Measured pixel geometry of YouTube thumbnail and title shelves, with provenance.

    Stale Official MCP Registry, com.engagedviews Updated 2 months ago 2 notes

    https://github.com/Jesse-Lucas1996/agentic-business/releases/download/v1.0.2/engagedviews-surfaces.mcpb@1.0.2
  22. glamour

    MCP servers

    Browser-measured visual debugging and verification tools for coding agents.

    Stale Official MCP Registry, io.github.gratise Updated 50 days ago 1 note

    glamour-mcp@0.2.0
  23. Droste

    MCP servers

    Local code exploration with progressive zoom and measured token budgets.

    Stale Official MCP Registry, io.github.lorismascio17 Updated 28 days ago 1 note

    droste-memory@1.3.0
  24. Bindingdb

    MCP servers

    BindingDB — measured protein/small-molecule binding affinities.

    Stale Official MCP Registry, io.github.pipeworx-io Updated 17 days ago 3 notes

    @pipeworx/mcp-bindingdb@0.2.1

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.