Skip to main content
Glama
knowledge-curator-mcp

knowledge-curator-mcp

by Ryu07-d

knowledge-curator-mcp

A local, zero-cost MCP server that fact-checks your Markdown / Obsidian notes.

It uses a local LLM via Ollama to extract claims and judge them against free, key-less sources (Wikipedia + DuckDuckGo). No cloud API, no API keys, nothing leaves your machine except the public search queries.

Unlike naive fact-checkers that count search hits, this server has the LLM read each source and decide whether it supports, contradicts, or is insufficient for the claim.

Why local?

  • No cost — runs entirely on your own machine.

  • Private — your notes are never sent to a cloud LLM.

  • Good enough — a small instruct model (3–7B) is plenty for "does this evidence support this sentence?" entailment judgments.

Related MCP server: Personal Notes Assistant

Requirements

  • Node.js ≥ 18 (uses the global fetch)

  • Ollama running locally with an instruct model pulled:

ollama pull qwen2.5:3b   # default — ~1.9GB, strong instruction-following
# alternatives: qwen3.5:4b (better), qwen2.5:7b (best, ~4.7GB)

A general instruct model is recommended over a persona/style fine-tune: fact-checking needs neutral, accurate reading, not a personality.

Install & build

npm install
npm run build

Configure your MCP client

Add to your Claude Desktop config (claude_desktop_config.json):

{
  "mcpServers": {
    "knowledge-curator": {
      "command": "node",
      "args": ["/absolute/path/to/knowledge-curator-mcp/build/index.js"],
      "env": {
        "OLLAMA_MODEL": "qwen2.5:3b"
      }
    }
  }
}

Environment variables

Variable

Default

Description

OLLAMA_HOST

http://localhost:11434

Ollama server URL

OLLAMA_MODEL

qwen2.5:3b

Any installed Ollama model

WIKI_LANG

ja

Wikipedia language edition (en, ja, ...)

Tools

Tool

What it does

verify_claim

Verify a single statement; returns a verdict + citations.

fact_check_document

Extract & verify claims in a file; optional auto_fix inserts notes.

add_citations

Fact-check a file and insert footnote citations for claims that need them.

scan_vault_for_issues

Walk an Obsidian vault and report files with contradicted/uncited claims.

git_commit_corrections

Commit corrected files to git.

Verdicts

Verdict

Meaning

✅ verified

Evidence clearly supports the claim.

❌ incorrect

Evidence clearly contradicts it (a correction is suggested).

📝 needs_citation

Plausible & on-topic, but evidence doesn't directly confirm.

❓ unverifiable

Evidence unrelated or insufficient.

Example

"Verify: 日本の首都は大阪である。"

**Verdict**: ❌ incorrect (90% confidence)
**Reasoning**: Evidence clearly contradicts the claim that '日本の首都は大阪である'.
**Sources**: Wikipedia: 大阪市, Wikipedia: 首都圏 (日本), ...
**Suggested correction**: 日本の首都は東京である。

Case study

See docs/case-study.md for an end-to-end walkthrough: ingesting PDFs into Markdown locally, then fact-checking the claims — including the example above where a naive hit-counter would be fooled but the LLM catches the error.

How it works

note.md ──▶ [LLM extracts claims] ──▶ for each claim:
                                         ├─ Wikipedia search (intro extracts)
                                         ├─ DuckDuckGo instant answer
                                         └─ [LLM reads evidence → verdict + citation]

Limitations

  • Quality scales with the model. A 3B model occasionally produces a sloppy rationale; use qwen3.5:4b/qwen2.5:7b for tougher material.

  • Free sources are shallow: Wikipedia covers general/encyclopedic facts well, but niche or very recent claims will often come back unverifiable.

  • auto_fix edits files in place — keep your notes under version control.

License

MIT

Available Tools

5 tools
add_citationsB

Fact-check a file and automatically insert citations for claims that need them.

Inputs: file_path (required), citation_style.

fact_check_documentA

Fact-check a Markdown/Obsidian note using a local LLM (Ollama) and free sources (Wikipedia, DuckDuckGo). Identifies claims that are verified, contradicted, or need a citation.

Inputs: file_path (required), auto_fix, check_level.

git_commit_correctionsC

Commit corrected files to git.

Inputs: file_paths (required), message.

scan_vault_for_issuesB

Scan an entire Obsidian vault and report files containing claims that are contradicted or need citations.

Inputs: vault_path (required), output_report, exclude_patterns.

verify_claimA

Verify a single claim with a local LLM against free sources, returning a verdict and citations.

Inputs: claim (required), context.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.4/5.0

    Scored across 5 tools

    Disambiguation4/5

    Tools are mostly distinct but add_citations and fact_check_document both operate on files and could be confused; one inserts citations while the other reports. scan_vault_for_issues is a batch version of fact_check_document, adding slight overlap.

    Naming Consistency3/5

    Most tools follow verb_noun (add_citations, fact_check_document, verify_claim) but git_commit_corrections and scan_vault_for_issues break the pattern with prepositional phrases or compound nouns, creating mild inconsistency.

    Tool Count5/5

    With 5 tools, the set is well-scoped for a knowledge curator. Each tool serves a clear purpose without redundancy, and the count feels neither sparse nor overwhelming.

    Completeness4/5

    The tools cover the essential workflow: verify claims, fact-check documents, add citations, scan vaults, and commit. Minor gaps exist (e.g., no tool for reverting changes or editing citations manually), but core operations are present.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Local-first MCP server that extracts structured knowledge from markdown notes into SQLite with full-text search, enabling AI coding tools to retrieve relevant context offline at zero cost.
      3
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      MCP server for local-first RAG over Obsidian vaults, enabling AI agents to search and ask questions about notes with grounded citations.
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      A local MCP server that turns an Obsidian vault into a searchable second brain for Claude with meaning-based search, note read/write, and insight reports like contradictions and stale TODOs.
      MIT