{
  "markdown": "<!-- mcp-name: io.github.onetrueclaude-creator/mcp-knowledge-gaps -->\n\n# mcp-knowledge-gaps\n\n**Find what your knowledge base mentions but doesn't actually explain.**\n\nFind concepts mentioned but never defined in your markdown knowledge base\n(Obsidian vault, Logseq graph, any folder of .md files). Uses fuzzy\ncanonicalization to avoid false positives, ranks gaps by frequency ×\nregion-diversity × novelty, generates prioritized research questions,\nand samples from the long tail via sortition to break confirmation\nbias in your research queue.\n\n\n## Install\n\n```bash\npip install mcp-knowledge-gaps\n# or\nuvx mcp-knowledge-gaps\n```\n\n## Usage\n\n### Claude Code\n\n```bash\nclaude mcp add mcp-knowledge-gaps -- mcp-knowledge-gaps\n```\n\n### Claude Desktop\n\nAdd to `claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"knowledge_gaps\": {\n      \"command\": \"uvx\",\n      \"args\": [\"mcp-knowledge-gaps\"]\n    }\n  }\n}\n```\n\n## MCP Tools\n\n| Tool | Tier | Description |\n|------|------|-------------|\n| `find_gaps` | Free | Scan a markdown vault and return concepts mentioned in multiple notes but without their own dedicated note. Applies fuzzy canonicalization and noise filtering. |\n| `list_gaps_by_priority` | Free | Return gaps ranked by priority: frequency × diversity × novelty (higher = fill this gap first). |\n| `generate_research_questions` | **Pro** | Generate prioritized research questions for the top N gaps. Each question comes with a priority score and factor breakdown. |\n| `surprise_research_topic` | **Pro** | Sortition sampling — pick a random gap from the LOW-priority long tail. Breaks confirmation bias by surfacing topics you'd never pick yourself. |\n| `export_review_queue` | **Pro** | Export a CSV of top-priority gap concepts, suitable for Anki or other spaced-repetition tools. Writes to output_csv and returns the row count. |\n\n\n## Pro tier\n\nUnlocks research question generation with RL-weighted ranking, sortition sampling of long-tail gaps, and CSV review queue export.\n\nLicense activation — any one of these works:\n\n```bash\n# 1. Environment variable\nexport KNOWLEDGE_GAPS_LICENSE=\"eyJhbGc...\"\n\n# 2. CLI flag\nmcp-knowledge-gaps --license-key \"eyJhbGc...\"\n\n# 3. Config file\necho \"eyJhbGc...\" > ~/.mcp-knowledge-gaps/license.jwt\n```\n\nLicenses are verified fully offline — no phone-home, no activation server. Get a license at **https://github.com/onetrueclaude-creator/mcp-knowledge-gaps#pro-tier**.\n\n## Requirements\n\n- Python 3.10+\n\n## License\n\nMIT\n",
  "bytes": 2466,
  "sha": "74bda798c79e261ad2b458f38393d902c6307376d8214b9a515f25b6e92d6373",
  "repo_slug": "onetrueclaude-creator/mcp-knowledge-gaps",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_onetrueclaude_creator_mcp_know_f7765b3f/readme"
}