knowledge-curator-mcp
A local, zero-cost MCP server that fact-checks your Markdown/Obsidian notes using a local LLM (Ollama) and free public sources (Wikipedia + DuckDuckGo) — no API keys or cloud services required.
Verify a single claim (
verify_claim): Submit any statement and receive a verdict (verified, incorrect, needs_citation, or unverifiable), confidence score, reasoning, sources used, and a suggested correction if wrong.Fact-check an entire document (
fact_check_document): Extract and verify claims from a Markdown file at configurable depth levels (basic: 5 claims, thorough: 15, academic: 50). Optionally auto-fix by applying corrections/citations directly to the file.Automatically insert citations (
add_citations): Fact-check a file and insert footnote-style citations for claims that need sourcing.Scan an Obsidian vault (
scan_vault_for_issues): Walk an entire vault directory to identify files with contradicted or uncited claims, with support for exclude patterns (e.g. templates, daily notes) and optional report output.Commit corrections to git (
git_commit_corrections): Commit auto-fixed files to a git repository with an optional custom commit message.
Uses DuckDuckGo search as a free, key-less source to gather instant answers and evidence for fact-checking claims.
Provides a tool to commit corrected files to git, enabling version control of auto-fixed notes.
Fact-checks Markdown notes in Obsidian vaults, scanning files for contradicted or uncited claims and optionally inserting citations or corrections.
Leverages local Ollama models (e.g., qwen2.5:3b) to extract claims from notes and judge evidence for entailment without any cloud API.
Queries Wikipedia as a free, authoritative source to retrieve introductory extracts and verify factual claims.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@knowledge-curator-mcp verify the claim that the capital of Japan is Osaka"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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 buildConfigure 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 server URL |
|
| Any installed Ollama model |
|
| Wikipedia language edition ( |
Tools
Tool | What it does |
| Verify a single statement; returns a verdict + citations. |
| Extract & verify claims in a file; optional |
| Fact-check a file and insert footnote citations for claims that need them. |
| Walk an Obsidian vault and report files with contradicted/uncited claims. |
| Commit corrected files to git. |
Verdicts
Verdict | Meaning |
✅ | Evidence clearly supports the claim. |
❌ | Evidence clearly contradicts it (a correction is suggested). |
📝 | Plausible & on-topic, but evidence doesn't directly confirm. |
❓ | 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/qwen2.5:7bfor tougher material.Free sources are shallow: Wikipedia covers general/encyclopedic facts well, but niche or very recent claims will often come back
unverifiable.auto_fixedits files in place — keep your notes under version control.
License
MIT
Available Tools
5 toolsadd_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
Scored across 5 tools
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.
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.
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.
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
Related MCP Connectors
Markdown-based note-taking with a hosted MCP server. Your notes serve you and your AI.
Hosted MCP server for Obsidian Sync vaults: read, search, edit notes. Not affiliated with Obsidian.
Serve a folder of Markdown notes as an MCP server: hybrid search, reading, and sourced answers.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceLocal-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.3MIT
- AlicenseNot gradedqualityDmaintenanceMCP server that indexes your Obsidian notes into a Milvus vector database and enables querying them via a local or OpenAI LLM, with real-time synchronization.3MIT
- AlicenseNot gradedqualityDmaintenanceMCP server for local-first RAG over Obsidian vaults, enabling AI agents to search and ask questions about notes with grounded citations.MIT
- AlicenseNot gradedqualityDmaintenanceA 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