MCP.Market

Gnosis MCP server

by nicholasglazer·io.github.nicholasglazer/gnosis·v0.17.5·29 stars
No reviews yet

Zero-config MCP server for searchable documentation. SQLite or PostgreSQL.

A85/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A85/100

full report

Adoption
Growing

29 stars151 downloads/wk

Reviews

Write one

Nobody has reviewed Gnosis MCP yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Gnosis MCP tools (9, 3 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • delete_docwrite action

    Delete a document and all its chunks. Requires GNOSIS_MCP_WRITABLE=true.

  • get_context

    Get the most important documents as a lightweight context primer.

  • get_doc

    Get full document content by file path. Reassembles all chunks in order.

  • get_graph_stats

    Get knowledge graph topology: orphans, hubs, connection stats.

  • get_related

    Find documents related to a given path via incoming and outgoing links.

  • search_docs

    Search documentation using keyword or hybrid semantic+keyword search.

  • search_git_history

    Search git commit history documents. Searches the git-history category.

  • update_metadatawrite action

    Update metadata fields on all chunks of a document. Requires GNOSIS_MCP_WRITABLE=true.

  • upsert_docwrite action

    Insert or replace a document. Requires GNOSIS_MCP_WRITABLE=true.

Public scan report

scanner v0.1.10 · 2026-10-15 · same rubric, same numbers if you re-run it

1 medium
  • Code scan28 source files scanned20/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Findings (1)

  • mediumeval / new Function usedexec.eval
    gnosis_mcp-0.17.5/src/gnosis_mcp/cli.py: …ser("eval", help="Run retrieval quality eval (Hit@K, MRR, Precision@K)") p_eval.ad…
Overall 85/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Gnosis MCP compares

Against every graded Databases MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
85/100
higher than 65% of 802 Databases servers
Tools
9
the typical Databases server has 8
Tools that change things
33%
typical: 10%. Fewer write tools means less an agent can break
GitHub stars
29
more than 86% of 602 Databases servers
Downloads a week
151
more than 66% of 328 Databases servers with a package

What its tools let an agent do: 6 read · 2 change · 1 delete

Install Gnosis MCP in Claude Code, Cursor or VS Code

claude mcp add gnosis -- uvx gnosis-mcp
Add to Cursor

What the publisher says

From the Gnosis MCP repository's README, as published. We do not edit it. Read it on GitHub

<!-- mcp-name: io.github.nicholasglazer/gnosis -->

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 &middot; Documentation &middot; Tools &middot; Configuration &middot; Full Reference

Ingest docs &rarr; Search with highlights &rarr; Stats overview &rarr; 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

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Grade history

  • 2026-09-19restoreB → Ascore 85: eval / new Function used

Gnosis MCP: common questions

Is Gnosis MCP server safe?
Yes, by our scan: it is graded A (85/100). Read the Gnosis MCP safety report
How do I install Gnosis MCP?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Gnosis MCP need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Gnosis MCP maintained?
The last commit was 20 days ago (2026-10-15). The latest release is v0.17.5.
What can I use instead of Gnosis MCP?
Servers from other publishers that do the same job: DBHub MCP server, Faucet MCP server and memo MCP server. Compare all Gnosis MCP alternatives.
How does Gnosis MCP compare with other Databases MCP servers?
safety score 85/100 (higher than 65% of 802 Databases servers); tools 9 (the typical Databases server has 8); tools that change things 33% (typical: 10%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Gnosis MCP

Same job from other publishers: the closest match first, then the best rated.

All Gnosis MCP alternatives →
  • DBHub
    Token-efficient database MCP server for PostgreSQL, MySQL, MariaDB, SQL Server, Oracle, SQLite
    A
  • Faucet
    SQL database to MCP tools and REST API: PostgreSQL, MySQL, SQL Server, Oracle, SQLite, Snowflake.
    A
  • memo
    Memory for AI agents — MLX (Apple Silicon) or CPU (Linux), sqlite-vec + BM25, zero cloud.
    A
  • NeoSQL MCP
    Schemas, SQL, ERDs, and codegen for PostgreSQL, MySQL, Oracle, SQLite, and more via NeoSQL Desktop.
    A
  • DB Explorer
    Read-only SQL for PostgreSQL, MySQL and SQLite: schema, safe SELECTs, EXPLAIN, index advice
    B