Plugin

gnosis

Name: gnosis
Author: nicholasglazer

Ingest local files, git history, or crawled websites into a local SQLite/PostgreSQL knowledge base for semantic/hybrid search and RAG. Manage CRUD, tune retrieval with metrics like nDCG/MRR, load usage-weighted context into AI sessions, and audit doc-code drift via zero-config MCP server.

npx claudepluginhub nicholasglazer/gnosis-mcp

Component Overview

Agents

Skills

Hooks

MCP Servers

Component Details

Agents (6)

Agents for gnosis-mcp

/README

Subagent definitions for [Claude Code](https://docs.anthropic.com/en/docs/claude-code)

context-loader

/context-loader

Lightweight context primer — loads relevant docs into conversation context before starting work. Use at the beginning of tasks to prime with architectural knowledge.

corpus-sync

/corpus-sync

Bulk-ingestion specialist — runs the full ingest / re-ingest / prune / crawl / git-history lifecycle via shell commands. Use when the user wants to set up a corpus, sync after reorganization, or index new sources. Complements doc-keeper (which does single-file CRUD).

doc-explorer

/doc-explorer

Fast documentation navigator — search, read, follow the link graph, cross-reference code. Read-only. Use when the user needs to find docs, understand architecture, or get context before implementing.

doc-keeper

/doc-keeper

Documentation maintainer — index new docs, update stale content, run the full corpus lifecycle (files, git history, web crawl, prune, re-ingest). Use after features, reorganizations, or when docs drift from code.

doc-reviewer

/doc-reviewer

Code-aware documentation reviewer — checks docs for accuracy against the actual codebase. Use before releases or after major refactors to catch doc drift.

Skills (8)

context

/context

Load usage-weighted context from Gnosis MCP. Surfaces most-accessed docs for session startup or topic primers.

eval

/eval

Measure retrieval quality on your corpus — Hit@5, MRR, nDCG@10, Precision@5. Thin wrapper around `gnosis-mcp eval` with regression tracking against a saved baseline, plain-English interpretation, and tuning pointers when numbers look off. Use after every ingest or config change.

ingest

/ingest

Populate the gnosis-mcp knowledge base — from local files, git history, or a crawled website. Handles the full matrix of flags (--force, --prune, --wipe, --embed, --include-crawled) in one place.

manage

/manage

CRUD operations on the knowledge base — add, delete, update metadata. For bulk ingest / re-ingest / prune, use /gnosis:ingest instead. Requires GNOSIS_MCP_WRITABLE=true.

/search

Search the gnosis-mcp knowledge base. Keyword (default), hybrid semantic+keyword (--semantic), or git commit history (--git). Includes sanity checks and a reranker warning.

setup

/setup

First-time setup wizard for Gnosis MCP. Install, init the database, ingest a docs folder, wire your editor — in that order.

status

/status

Verify gnosis-mcp server connectivity, schema integrity, and corpus health. Use when MCP calls fail, return empty, or return unexpected data.

tune

/tune

Find the chunk-size and retrieval config that maximizes quality on YOUR corpus. Sweeps chunk sizes, runs a golden-query set, reports nDCG / MRR / Hit@5. Use after first ingest or whenever your corpus changes shape significantly.

Hooks (1)

Review workflow modifications before installing

Event Hooks

1 hook across 1 event

MCP Servers (1)

Connects to external services

gnosis

README

Gnosis MCP

Stop pasting files into context. Your AI agent searches your local docs instead.
5–10× fewer tokens per lookup. 92 % Hit@5 on real dev docs. Zero cloud dependencies.

Quick Start · Git History · Web Crawl · Backends · Editors · Tools · Embeddings · Full Reference

_{Ingest docs → Search with highlights → Stats overview → Serve to AI agents}

Without a docs server

LLMs hallucinate API signatures that don't exist
Entire files dumped into context — 3,000–15,000 tokens per doc
Architecture decisions buried across dozens of files
Every repeated lookup pays full context cost

With Gnosis MCP

search_docs returns ranked, highlighted excerpts — typically 300–800 tokens
Real answers grounded in your actual docs, not guesses from training data
One local index across hundreds of files — instant multi-doc search
5–10× token savings per lookup when your corpus covers the question

What makes gnosis-mcp different

Your data stays on your machine. SQLite by default, PostgreSQL at scale — nothing leaves the host.
Index anything that's docs-shaped. Markdown, git commit history, crawled websites — one index, one search API.
Measured, not marketed. Ships BEIR SciFact numbers (0.671 nDCG@10 — within 1 % of the Lucene BM25 baseline), a reproducible eval harness (gnosis-mcp eval), and a chunk-size sweep showing where the quality plateau actually sits.

Full side-by-side vs Context7 / docs-mcp-server / mcp-local-rag: gnosismcp.com#compare.

Features

Zero config — SQLite by default, pip install and go
Hybrid search — keyword (BM25) + semantic (local ONNX embeddings, no API key). Tune RRF fusion with GNOSIS_MCP_RRF_K.
Cross-encoder reranking — optional [reranking] extra with a 22M-param ONNX model. Off by default. Test on your own corpus before enabling — the bundled MS-MARCO reranker hurts dev-doc retrieval in our measurements.
Git history — ingest commit messages as searchable context (ingest-git)
Web crawl — ingest documentation from any website via sitemap or link crawl
Multi-format — .md .txt .ipynb .toml .csv .json + optional .rst .pdf
Auto-linking — relates_to frontmatter creates a navigable document graph
Watch mode — auto-re-ingest on file changes
Prune stale docs — gnosis-mcp ingest --prune removes chunks whose source file was deleted. --wipe for a full reset before re-ingest.
Built-in eval harness — gnosis-mcp eval prints Hit@K / MRR / Precision@K in one command
PostgreSQL ready — pgvector + tsvector when you need scale

Performance

Fast. 8.7 ms mean MCP round-trip. Hybrid search p50 < 30 ms on a 700-doc corpus. Keyword QPS scales from 9,463 @ 100 docs to 471 @ 10,000 docs (full numbers).

Finds the right answer. On 558 real dev docs with 25 hand-written golden queries: Hit@5 = 0.92, nDCG@10 = 0.87, MRR = 0.79. On BEIR SciFact (5,183 docs, public retrieval benchmark): nDCG@10 = 0.671 — within 1 % of the Lucene BM25 baseline.

Tokens saved. Each search_docs call returns 200–500 tokens of on-point snippets instead of the 3,000–15,000 tokens a full-file Read would have cost. Track your own with gnosis-mcp savings (v0.12.0+) — the ledger writes to search_access_log on every call and aggregates per tool per --days N:

View full README on GitHub

Similar Plugins

agent-knowledge

Clone repos, crawl docs, search locally. Fast, authoritative answers for AI coding agents.

Stats

Version0.13.3

Stars17

Forks5

MaintenanceExcellent

LicenseMIT

Last CommitApr 19, 2026

AddedApr 2, 2026

Actions

View on GitHub View README Plugin Marketplace JSON

Safety Signals

Caution

Uses power tools

Uses Bash, Write, or Edit tools

Help us improve

Share bugs, ideas, or general feedback.

Back to Plugins

Gnosis MCP

Stop pasting files into context. Your AI agent searches your local docs instead.
5–10× fewer tokens per lookup. 92 % Hit@5 on real dev docs. Zero cloud dependencies.

Quick Start · Git History · Web Crawl · Backends · Editors · Tools · Embeddings · Full Reference

_{Ingest docs → Search with highlights → Stats overview → Serve to AI agents}

Without a docs server

LLMs hallucinate API signatures that don't exist
Entire files dumped into context — 3,000–15,000 tokens per doc
Architecture decisions buried across dozens of files
Every repeated lookup pays full context cost

With Gnosis MCP

search_docs returns ranked, highlighted excerpts — typically 300–800 tokens
Real answers grounded in your actual docs, not guesses from training data
One local index across hundreds of files — instant multi-doc search
5–10× token savings per lookup when your corpus covers the question

What makes gnosis-mcp different

Your data stays on your machine. SQLite by default, PostgreSQL at scale — nothing leaves the host.
Index anything that's docs-shaped. Markdown, git commit history, crawled websites — one index, one search API.
Measured, not marketed. Ships BEIR SciFact numbers (0.671 nDCG@10 — within 1 % of the Lucene BM25 baseline), a reproducible eval harness (gnosis-mcp eval), and a chunk-size sweep showing where the quality plateau actually sits.

Full side-by-side vs Context7 / docs-mcp-server / mcp-local-rag: gnosismcp.com#compare.

Features

Zero config — SQLite by default, pip install and go
Hybrid search — keyword (BM25) + semantic (local ONNX embeddings, no API key). Tune RRF fusion with GNOSIS_MCP_RRF_K.
Cross-encoder reranking — optional [reranking] extra with a 22M-param ONNX model. Off by default. Test on your own corpus before enabling — the bundled MS-MARCO reranker hurts dev-doc retrieval in our measurements.
Git history — ingest commit messages as searchable context (ingest-git)
Web crawl — ingest documentation from any website via sitemap or link crawl
Multi-format — .md .txt .ipynb .toml .csv .json + optional .rst .pdf
Auto-linking — relates_to frontmatter creates a navigable document graph
Watch mode — auto-re-ingest on file changes
Prune stale docs — gnosis-mcp ingest --prune removes chunks whose source file was deleted. --wipe for a full reset before re-ingest.
Built-in eval harness — gnosis-mcp eval prints Hit@K / MRR / Precision@K in one command
PostgreSQL ready — pgvector + tsvector when you need scale

Performance

Fast. 8.7 ms mean MCP round-trip. Hybrid search p50 < 30 ms on a 700-doc corpus. Keyword QPS scales from 9,463 @ 100 docs to 471 @ 10,000 docs (full numbers).

gnosis

Component Overview