nicholasglazer/gnosis-mcp

消毒剂

停止粘贴文件为上下文 。 你的人工智能特工正在搜索你的本地文件 5–10×每次检查会减少代币. 92%在真实的dev docs上点击"5". ○解云依缘.

快速启动( Middot;) 文档 & middot; 工具( Middot;) 配置( Middot;) 充分参考

Ingest Docs & rarr; 有要闻 & rarr; Stats 概览 & rarr; 向AI 代理服务

– – . . .

没有文件服务器

• LLMS幻觉API签名不存在
• 全部文件倒入上下文——每名医生3 000至15 000个令牌
• 数十个档案的建筑决定
• 每一次反复检查都要支付全部上下文费用

使用克诺斯MCP

• search_docs 回报排名,突出显示的节选——一般为300-800个令牌
• 真正的答案基于你的实际文件,而不是来自训练数据的猜测
• 百份文件的本地索引——即时多文件搜索
• 5-10x 象征性储蓄

– – . . .

□是什么让小说Mcp不同

• 你的数据留在机器上 SQLite默认为"PostgreSQL" 缩放——没有东西离开主机.
• 任何有文件形状的东西.

---

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