Mcp Knowledge Gaps

io.github.onetrueclaude-creatorPublished by GitHub account onetrueclaude-creatorv0.1.0Updated Oct 24, 2026

Find what your knowledge base mentions but doesn't actually explain.

VerifiedSTDIODesktop onlyFiles & StorageKnowledge & MemoryData & Analytics

Overview

AI-generated overview

Scans a local markdown knowledge base to find concepts that are mentioned repeatedly but never given their own note.

What you can do
It scans a folder of markdown notes, such as an Obsidian vault or Logseq graph, and returns concepts that appear across multiple notes without a dedicated note of their own. Fuzzy canonicalization and noise filtering reduce false positives, and gaps are ranked by frequency, region diversity and novelty. Pro tools generate prioritized research questions, sample low-priority long-tail gaps at random, and export a CSV review queue.
When to use it
Useful when you maintain a large markdown knowledge base and want to find underdeveloped topics or decide what to research or write next. It suits personal note vaults and research collections rather than general document search.
Requirements
Runs locally over stdio and needs Python 3.10 or later, installed via pip or run with uvx. It is desktop-only and has no remote endpoint. The optional Pro license is supplied through the KNOWLEDGE_GAPS_LICENSE environment variable, a CLI flag, or a license file.
Before you install
The Pro tools require a license token passed as KNOWLEDGE_GAPS_LICENSE; licenses are verified offline, so the token stays on the machine. The export tool writes a CSV file to a path you specify. The server reads your markdown vault, so point it only at folders you are willing to have scanned.

Installation

In SourceWeft

  1. Open Mcp Knowledge Gaps in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

mcp-knowledge-gaps

Find what your knowledge base mentions but doesn't actually explain.

Find concepts mentioned but never defined in your markdown knowledge base (Obsidian vault, Logseq graph, any folder of .md files). Uses fuzzy canonicalization to avoid false positives, ranks gaps by frequency × region-diversity × novelty, generates prioritized research questions, and samples from the long tail via sortition to break confirmation bias in your research queue.

Install

bash
pip install mcp-knowledge-gaps# oruvx mcp-knowledge-gaps

Usage

Claude Code

bash
claude mcp add mcp-knowledge-gaps -- mcp-knowledge-gaps

Claude Desktop

Add to claude_desktop_config.json:

json
{  "mcpServers": {    "knowledge_gaps": {      "command": "uvx",      "args": ["mcp-knowledge-gaps"]    }  }}

MCP Tools

ToolTierDescription
find_gapsFreeScan a markdown vault and return concepts mentioned in multiple notes but without their own dedicated note. Applies fuzzy canonicalization and noise filtering.
list_gaps_by_priorityFreeReturn gaps ranked by priority: frequency × diversity × novelty (higher = fill this gap first).
generate_research_questionsProGenerate prioritized research questions for the top N gaps. Each question comes with a priority score and factor breakdown.
surprise_research_topicProSortition sampling — pick a random gap from the LOW-priority long tail. Breaks confirmation bias by surfacing topics you'd never pick yourself.
export_review_queueProExport a CSV of top-priority gap concepts, suitable for Anki or other spaced-repetition tools. Writes to output_csv and returns the row count.

Pro tier

Unlocks research question generation with RL-weighted ranking, sortition sampling of long-tail gaps, and CSV review queue export.

License activation — any one of these works:

bash
# 1. Environment variableexport KNOWLEDGE_GAPS_LICENSE="eyJhbGc..."
# 2. CLI flagmcp-knowledge-gaps --license-key "eyJhbGc..."
# 3. Config fileecho "eyJhbGc..." > ~/.mcp-knowledge-gaps/license.jwt

Licenses are verified fully offline — no phone-home, no activation server. Get a license at https://github.com/onetrueclaude-creator/mcp-knowledge-gaps#pro-tier.

Requirements

  • Python 3.10+

License

MIT

Source: README.md at commit cbe9d93

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts