InnerVault

Library

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

Results

  1. json_repair

    AI repositories

    Repair malformed JSON from LLMs, APIs, logs, and user input in Python.

    Stale GitHub, mangiucugna 5,136 ★MITUpdated 6 days ago

    git clone https://github.com/mangiucugna/json_repair.git
  2. Cloudflare Workers MCP server: llm-output-quality-monitor

    Stale Official MCP Registry, io.github.lazymac2x Updated 6 months ago 1 note

  3. fluent-korean

    Prompts

    Claude Code가 명확한 한국어를 구사하게 만드는 output-style 플러그인 | Claude Code output-style for clear, fluent Korean

    Stale GitHub, snflkd 1,405 ★MITUpdated 2 months ago

    git clone https://github.com/snflkd/fluent-korean.git
  4. AI/LLM agent output audit MCP: policy eval, tamper-evident chain, AI safety, x402 USDC on Base.

    Stale Official MCP Registry, com.fronesislabs Updated 3 months ago 1 note

  5. VeriGhost-Clarity

    MCP servers

    Hallucination validator and factual grounding checker for LLM outputs.

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

  6. mcp-server

    MCP servers

    Detect fabrication and hallucination in any LLM output. 30+ models supported.

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

    @arkheia/mcp-server@0.1.4
  7. AISchemaGate validates and repairs structured LLM output against a contract, plus DataContractGate.

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

    @nightmoose/contractgate-mcp-server@0.4.1
  8. LLMVerify

    MCP servers

    Local-first MCP server for LLM output verification — risk signals, injection and PII checks.

    Stale Official MCP Registry, io.github.subodhkc Updated 38 days ago 2 notes

    llmverify@1.8.0
  9. boundaryai

    MCP servers

    Deterministic runtime safety for AI agents: scan PII, gate tool actions, verify LLM output.

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

  10. blinkpdf

    MCP servers

    Render Markdown and LLM output into accessible PDF/UA-1 PDFs. No headless Chromium.

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

  11. pdf-report-generator

    MCP servers

    Generate professional PDF reports from LLM output — cover, TOC, tables, charts, 5 themes.

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

    @ctalasila/pdf-report-generator@1.0.1
  12. Overwing

    MCP servers

    Guardrails for LLM output: pass / fail / review verdicts and one recommended action. Hosted or npm.

    Stale Official MCP Registry, ai.overwing Updated 34 days ago 3 notes

    overwing-mcp@0.15.0
  13. rubrkit

    MCP servers

    MCP-native AI evaluation: rubric audits, eval suites, and proof reports for AI/LLM output.

    Stale Official MCP Registry, com.rubrkit Updated 4 months ago 1 note

  14. Proven

    MCP servers

    Judge AI-written Python: no invented packages or calls, no facts from memory, verified LLM output.

    Stale Official MCP Registry, io.github.malikabyl Updated 13 days ago 1 note

    proven-judge@0.2.0
  15. PHM Physics Check

    MCP servers

    Deterministic physics plausibility checks for LLM outputs and robotics data. Offline, stdlib-only.

    Stale Official MCP Registry, io.github.PHM-Audit Updated 11 days ago 1 note

    https://github.com/PHM-Audit/phm-lite-check/releases/download/v1.0.1/phm-lite-check-mcpb-1.0.1.mcpb
  16. Real-time LLM output verification with 6-dim contract validation and auto-failover across providers.

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

    correctover-mcp-server@1.0.7
  17. Fact-check LLM outputs with cited sources. API key: aihcc.cloud/keys.

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

  18. lens-mcp

    MCP servers

    Outside-in validation gate for AI-generated text; a separate model checks LLM output, fail-closed.

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

    @soulfield/lens-mcp@1.1.1
  19. JsonMend

    MCP servers

    Repair broken JSON from LLM output and validate it against a JSON Schema.

    Stale Official MCP Registry, dev.workers.mike-tusa.jsonmend Updated 32 days ago 1 note

  20. LLM output Mermaid diagram linting, unquoted bracket healing, and syntax normalization engine

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

    https://github.com/Alpha-Park/genpark-markdown-mermaid-syntax-lint-healer-skill/releases/download/v1.0.1/genpark-markdown-mermaid-syntax-lint-healer-skill.mcpb
  21. json-repair-mcp

    MCP servers

    Repairs malformed JSON from LLM output, validated against a schema. Paid per call via Stripe.

    Stale Official MCP Registry, io.github.grupoanesthy-spec Updated 2 months ago 2 notes

    json-repair-mcp@1.0.1
  22. Token entropy and n-gram perplexity analyzer auditing LLM outputs for degenerate repetition loops an

    Stale Official MCP Registry, io.github.alphaparkinc Updated 27 days ago 1 note

    https://github.com/Alpha-Park/genpark-entropy-hallucination-detector-skill/releases/download/v1.0.1/genpark-entropy-hallucination-detector-skill-v1.0.1.mcpb
  23. Eval Engine API

    MCP servers

    Pay-per-call AI evaluation MCP server. Score LLM outputs against benchmark rubrics via Workers AI.

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

  24. write-human

    Skills

    Statistical linter that flags the words, phrases and constructions that make text read as LLM output, measured against billions of words people wrote before 2022. Runs offline. CLI on npm plus an Agent Skill for coding agents.

    Stale GitHub, arslanrakh 12 ★MITUpdated 11 days ago

    git clone https://github.com/arslanrakh/write-human.git

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.