
Mcp Knowledge Gaps
Scans your markdown knowledge base (Obsidian, Logseq, or any folder of .md files) and surfaces concepts that appear across multiple notes but never get their own explanation. The free tier gives you find_gaps and list_gaps_by_priority, which rank missing concepts by frequency, diversity, and novelty. Pro adds generate_research_questions for guided learning, surprise_research_topic for sortition sampling from the long tail to break confirmation bias, and export_review_queue to pipe gaps into spaced repetition tools. Licenses verify offline via JWT. Reach for this when your second brain has grown large enough that you've lost track of what you reference but never actually learned.
- tools
- 5
- auth
- Secret needed
- transport
- STDIO
- env var
- 1
- last updated
- Apr 18, 2026
Tools
5 toolsPublic tool metadata for what this MCP can expose to an agent.
find_gapsScan a markdown vault and return concepts mentioned in multiple notes but without their own dedicated note. Applies fuzzy canonicalization and noise filtering.
Scan a markdown vault and return concepts mentioned in multiple notes but without their own dedicated note. Applies fuzzy canonicalization and noise filtering.
No parameter schema in public metadata yet.
list_gaps_by_priorityReturn gaps ranked by priority: frequency × diversity × novelty (higher = fill this gap first).
Return gaps ranked by priority: frequency × diversity × novelty (higher = fill this gap first).
No parameter schema in public metadata yet.
generate_research_questionsGenerate prioritized research questions for the top N gaps. Each question comes with a priority score and factor breakdown.
Generate prioritized research questions for the top N gaps. Each question comes with a priority score and factor breakdown.
No parameter schema in public metadata yet.
surprise_research_topicSortition sampling — pick a random gap from the LOW-priority long tail. Breaks confirmation bias by surfacing topics you'd never pick yourself.
Sortition sampling — pick a random gap from the LOW-priority long tail. Breaks confirmation bias by surfacing topics you'd never pick yourself.
No parameter schema in public metadata yet.
export_review_queueExport a CSV of top-priority gap concepts, suitable for Anki or other spaced-repetition tools. Writes to output_csv and returns the row count.
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.
No parameter schema in public metadata yet.
Sponsors
Configuration
KNOWLEDGE_GAPS_LICENSEsecretPro license JWT (optional). Unlocks premium features. See README.
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
pip install mcp-knowledge-gaps
# or
uvx mcp-knowledge-gaps
Usage
Claude Code
claude mcp add mcp-knowledge-gaps -- mcp-knowledge-gaps
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"knowledge_gaps": {
"command": "uvx",
"args": ["mcp-knowledge-gaps"]
}
}
}
MCP Tools
Details
- Repository
- github.com/onetrueclaude-creator/mcp-knowledge-gaps
- Category
- Documents & Knowledge
- Package
mcp-knowledge-gaps- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active