InnerVault

Library

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

Results

  1. OpenTrain

    MCP servers

    Hire human data labelers, RLHF annotators, and evaluators from your coding agent.

    Stale Official MCP Registry, io.github.OpenTrain-AI Updated 5 months ago 2 notes

    @opentrain-ai/mcp@0.2.2
  2. Research Repo Doctor

    MCP servers

    Deterministic Artifact Evaluation preflight and run-path grader for research repositories.

    Stale Official MCP Registry, io.github.Tom409114 Updated 4 months ago 1 note

    rrdoctor@0.2.24
  3. Governance proxy for MCP servers — policy evaluation, human approval, audit trails.

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

    @sidclaw/sdk@0.1.13
  4. Braintrust

    MCP servers

    AI evaluation and observability platform — query experiments, logs, datasets, and prompts.

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

  5. PaperBanana-CN

    MCP servers

    Generate and evaluate academic diagrams and plots with independent model connections.

    Stale Official MCP Registry, io.github.mituan-ai Updated 3 months ago 1 note

    paperbanana-cn@2.0.1
  6. golden-dataset-mcp

    MCP servers

    Version-controlled golden datasets and RAG evaluation, no API key needed.

    Stale Official MCP Registry, io.github.nipunkhanderia Updated 4 months ago 1 note

    golden-dataset-mcp@0.1.2
  7. flippa-mcp

    MCP servers

    Search, analyze, and evaluate online businesses for sale on Flippa.com marketplace.

    Stale Official MCP Registry, io.github.sind00 Updated 9 months ago 2 notes

    flippa-mcp-server@1.0.2
  8. rhumb-mcp

    MCP servers

    Agent gateway for Index discovery, AN Score evaluation, and Resolve governed execution

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

    rhumb-mcp@0.8.2
  9. Basic arithmetic tools with natural-language expression parsing and evaluation.

    Stale Official MCP Registry, io.github.yarnabrina Updated 30 days ago 1 note

    mcp-learning@0.3.0
  10. AI Trainer Work

    Public APIs

    Open AI training jobs (RLHF, data annotation, expert evaluation) from 20+ platforms, with pay

    Indexed public-apis (GitHub list)

  11. truth-table-mcp

    MCP servers

    Evaluate boolean logic expressions and build full truth tables - fully local.

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

    @mrfentmen/truth-table-mcp@1.0.1
  12. evalsmith-mcp

    MCP servers

    Evaluate RAG retrieval, agent tool calls and prompt regressions with deterministic metrics.

    Stale Official MCP Registry, io.github.diegoperezg7 Updated 19 days ago 2 notes

    evalsmith-mcp@0.1.0
  13. mathjs-mcp

    MCP servers

    mathjs: evaluate any maths expression remotely with the math.js service - keyless.

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

    @mrfentmen/mathjs-mcp@1.0.0
  14. Callvu

    MCP servers

    Evaluate Callvu, the Completion and Compliance Layer: processes, proof, costs and procurement.

    Stale Official MCP Registry, com.callvu Updated 5 days ago 1 note

  15. Gridline

    MCP servers

    Fine-tune, evaluate and batch open models through Gridline's OpenAI-compatible API.

    Indexed Official MCP Registry, io.github.GridlineGPU Updated yesterday 2 notes

    @gridlinegpu/mcp@0.1.2
  16. Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model...

    Indexed OpenRouter model list, aion-labs Updated 21 months ago

    aion-labs/aion-rp-llama-3.1-8b
  17. pi-harness

    Agents & frameworks

    The operational superset of Pi Coding Agent — everything Pi, plus observability, governance, recovery, evaluation and multi-agent orchestration. Pi Coding Agent 的运维超集——完整继承 Pi 的核心能力,并进一步扩展可观测性、治理、故障恢复、评估和多 Agent 编排。

    Indexed GitHub, wangmiaozero 390 ★AGPL-3.0Updated today

    git clone https://github.com/wangmiaozero/pi-harness.git
  18. ADHD in Children

    MCP servers

    Clinician-reviewed library on ADHD in children — evaluation, treatment, school, parenting.

    Stale Official MCP Registry, ai.childadhd Updated 36 days ago 1 note

  19. Clinician-reviewed library on child psychiatric evaluation and medication decision-making.

    Stale Official MCP Registry, ai.childpsychiatry Updated 36 days ago 1 note

  20. Search 760K+ companies by technographics with direction of change: adopting, replacing, evaluating

    Stale Official MCP Registry, ai.echoloc Updated 3 months ago 1 note

  21. noveum

    MCP servers

    Trace, evaluate, and optimize your LLM, RAG, and agent apps with Noveum observability.

    Stale Official MCP Registry, ai.noveum Updated 3 months ago 1 note

  22. ADHD in Teens

    MCP servers

    Clinician-reviewed library on ADHD in teens — accommodations, executive function, evaluations.

    Stale Official MCP Registry, ai.teenadhd Updated 36 days ago 1 note

  23. aegis

    MCP servers

    Local stdio MCP server for the AEGIS governance client. The hosted evaluation service is offline.

    Stale Official MCP Registry, com.undercurrentholdings Updated 59 days ago 2 notes

    aegis-governance@1.4.2
  24. Seosa

    MCP servers

    AI web novel co-writer: series, characters, episodes, and quality evaluation. Korean-first.

    Stale Official MCP Registry, ink.seosa Updated 5 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.