gnosis-mcp: Instructions file for Claude Code

CLAUDE.md

gnosis-mcp CLAUDE.md is an instructions file for Claude Code from nicholasglazer/gnosis-mcp. It costs 3,017 tokens per session, scanned A, original, MIT.

A documentation server that stores files in SQLite or PostgreSQL and makes them searchable for coding agents. It can also provide self-hosted text embeddings, which turn text into numerical representations for similarity search.

In plain words
What is it for?
Use it to ingest documentation, search it with keyword or meaning-based queries, and provide an embeddings endpoint to other services.
Why use it?
It gives an agent a local or database-backed way to find relevant documentation instead of relying on memory or cloud search services.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is nicholasglazer/gnosis-mcp's own configuration. It tells Claude Code how to work on gnosis-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gnosis-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to nicholasglazer/gnosis-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/nicholasglazer/gnosis-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/nicholasglazer/gnosis-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for gnosis-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nicholasglazer/gnosis-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/nicholasglazer/gnosis-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nicholasglazer/gnosis-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nicholasglazer/gnosis-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for gnosis-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/nicholasglazer/gnosis-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nicholasglazer/gnosis-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,017 This file is loaded in full into every session.
When invoked 3,017 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.03017 $0.03017
Opus 5 $0.01509 $0.01509
Sonnet 5 $0.00603 $0.00603
Haiku 4.5 $0.00302 $0.00302

Measured 10d ago against content hash 05231633b861, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

gnosis-mcp CLAUDE.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

├── local_embed.py # Local ONNX embedding engine — stdlib urllib model download, CPU inference
CLAUDE.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gnosis MCP -- MCP Documentation Server

Open-source Python MCP server for searchable documentation. Zero-config SQLite default, PostgreSQL optional.

Dual-mode service (v0.14.0+): In addition to the Claude Code MCP (stdio) mode, gnosis-mcp runs as a production embeddings service — Dockerised, exposing POST /v1/embed (OpenAI-compatible) backed by local ONNX inference. External services use it as a self-hosted embeddings backend without calling any cloud API.

Architecture

src/gnosis_mcp/
├── backend.py         # DocBackend Protocol + create_backend() factory
├── pg_backend.py      # PostgreSQL backend — asyncpg pool, $N params, tsvector, pgvector, UNION ALL
├── sqlite_backend.py  # SQLite backend — aiosqlite, FTS5 + sqlite-vec hybrid (RRF), ? params
├── sqlite_schema.py   # SQLite DDL — tables, FTS5 virtual table, vec0 virtual table, sync triggers
├── config.py          # GnosisMcpConfig frozen dataclass, backend auto-detection, GNOSIS_MCP_* env vars
├── db.py              # Backend lifecycle + FastMCP lifespan context manager
├── server.py          # FastMCP server: 9 tools + 3 resources + auto-embed queries
├── ingest.py          # File ingestion + converters: multi-format (.md/.txt/.ipynb/.toml/.csv/.json + optional .rst/.pdf), smart chunking, hashing
├── crawl.py           # Web crawler: sitemap/BFS URL discovery, robots.txt, ETag caching, trafilatura HTML→markdown, rate-limited async fetching
├── parsers/           # Non-file ingest sources
│   ├── __init__.py    # Package init
│   └── git_history.py # Git log → searchable markdown: parse commits, group by file, render, ingest via existing pipeline
├── watch.py           # File watcher: mtime polling, debounce, auto-re-ingest + auto-embed on changes
├── schema.py          # PostgreSQL DDL — tables, indexes, HNSW, hybrid search functions
├── embed.py           # Embedding providers: openai/ollama/custom/local, batch backfill
├── local_embed.py     # Local ONNX embedding engine — stdlib urllib model download, CPU inference
└── cli.py             # argparse CLI: serve, init-db, ingest, ingest-git, crawl, search, embed, stats, export, diff, check, cleanup, fix-link-types

Read the full file on GitHub · 156 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 156 lines · 3,017 tokens per session scan A 05231633b861

Subscribe to this mod's changes

gnosis-mcp CLAUDE.md is an instructions file published in the GitHub repository nicholasglazer/gnosis-mcp (29 stars, last pushed 20d ago), licensed MIT. It adds 3,017 tokens to every session, about $0.0151 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens