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 judgethem against free, key-less sources (Wikipedia + DuckDuckGo). No cloud API, noAPI keys, nothing leaves your machine except the public search queries.

Unlike naive fact-checkers that count search hits, this server has the LLM read eachsource 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 evidencesupport this sentence?" entailment judgments.

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。

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 sloppyrationale; use qwen3.5:4b/qwen2.5:7b for tougher material.
Free sources are shallow: Wikipedia covers general/encyclopedic facts well, butniche or very recent claims will often come back unverifiable.
auto_fix edits files in place — keep your notes under version control.

License

MIT

knowledge-curator-mcp