liana-banyan/librarian-mcp

Developer tools

このページは AI により自動翻訳されています。技術的な詳細は原文をご確認ください。原文を見る

0 stars 19 forks 品質 69 トレンド 8NOASSERTION

Repository Install

Pre-curated canonical memory + prose/code provenance for any AI coding client. MCP-native.

概要

Pre-curated canonical memory + prose/code provenance checking + benchmark metrics, delivered as a Model Context Protocol server that works across Claude Code, Cursor, VSCode (via Continue), and any MCP-capable client. Independently measured result (Eyewitness Benchmark R10, April 2026, eight models across four vendors, 1,200 graded calls, inter-rater kappa 0.883/0.850): - mean 8.7% correct - mean 94.8% correct — - at 19x cost difference - Applied inside Microsoft Copilot's inference path, the same architecture recovers an estimated in waste. Inside Anthropic's developer tools, . Full methodology in the R9 Empirical Test Companion Paper. for union queries: intent='["benchmark", "founder_voice"]' No grant funding, no VC, no extractive margin. Cost+20% on operating expense. That's it. Because you shouldn't have to pick between your AI assistants. MCP servers work across Claude Code, Cursor (v0.45+), Continue (VSCode / JetBrains), Zed, and every MCP-capable client in the roadmap.

README

以下は原文 README の抜粋です。原文を見る。

Librarian MCP

pip install librarian-mcp

A real, measured alternative to “bigger context windows.” Pre-curated canonical memory + prose/code provenance checking + benchmark metrics, delivered as a Model Context Protocol server that works across Claude Code, Cursor, VSCode (via Continue), and any MCP-capable client.

Try it without installing →

What it does

Five tools, all exposed via MCP:

Tool	What it does	Added
`librarian_context`	Intent-aware canonical memory packet. Loads curated preload content scoped to your query intent (outreach, architecture, benchmark, founder voice, etc.). Eliminates the “forgets by prompt #21” failure mode.	v0.1.0 (stub), v0.2.0 (intent-aware)
`prose_provenance`	Deterministic drift detection between two document versions. Catches silently-removed voice anchors, stale canonical numbers, section changes, register shifts.	v0.1.0
`record_measurement`	Log a single benchmark measurement (vendor, model, condition, accuracy, cost, latency) to local JSONL.	v0.2.0
`metrics_summary`	Per-vendor and per-model aggregation of recorded measurements. Shows accuracy lift, cost savings, cache hit rate.	v0.2.0
`opt_in_share`	Toggle anonymous metrics sharing flag. Default OFF. Commons dashboard POST endpoint ships in a future release.	v0.2.0

Why we built this

Independently measured result (Eyewitness Benchmark R10, April 2026, eight models across four vendors, 1,200 graded calls, inter-rater kappa 0.883/0.850):

Without the Librarian (COLD): mean 8.7% correct
With the Librarian (HOT): mean 94.8% correct — 86.1 percentage-point lift
Haiku 4.5 (cheapest) ties Opus 4.7 (most expensive) at 19x cost difference
4.3x more right answers per dollar of compute

Applied inside Microsoft Copilot’s inference path, the same architecture recovers an estimated $750M/year in waste. Inside Anthropic’s developer tools, ~$130M/year. Full methodology in the R9 Empirical Test Companion Paper.

`librarian_context` — Intent API

librarian_context(intent="outreach", max_tokens=16000)

Intent	What it loads	Approx. tokens
`""` (default)	Base R9-v2 preload only	~4,500

GitHub で README 全文を見る

インストール

This server does not publish a one-line install command.

Open the repository installation guide MCP 初心者？mcpskill.org のガイドから始めましょう →

設定

{
  "mcpServers": {
    "librarian": {
      "command": "python",
      "args": ["-m", "librarian_mcp"]
    }
  }
}