Graphify Ts

@mohanagy

Graphify Ts について

Local MCP server and context compiler that turns TypeScript/Node workspaces into compact, verifiable context packs for AI coding agents.

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "graphify-ts": {
      "command": "npx",
      "args": [
        "-y",
        "@mohammednagy/graphify-ts@latest",
        "serve",
        "graphify-out/graph.json"
      ],
      "env": {
        "GRAPHIFY_TOOL_PROFILE": "core"
      }
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Graphify Ts?

Graphify Ts indexes a TypeScript/Node workspace (and PR diffs) into a local knowledge graph and compiles the graph into compact, verifiable context packs for AI coding agents. It runs entirely on your machine with no cloud dependencies and no API keys.

How to use Graphify Ts?

Install globally with npm install -g @mohammednagy/graphify-ts. Run graphify-ts generate . to build the knowledge graph, then graphify-ts claude install (or the equivalent command for Cursor, Copilot CLI, Gemini CLI, Aider, Codex CLI, OpenCode) to wire the agent via MCP or a context-pack-first profile. Use graphify-ts pack or graphify-ts prompt to produce a provider-ready prompt without MCP.

Key features of Graphify Ts

Local-first: no cloud required, your code never leaves your laptop.
Reduces per-session input tokens by up to 5.28× on measured benchmarks.
Supports PR review via pr_impact and review-compare tools.
Works with Claude Code, Cursor, Copilot CLI, Gemini CLI, Aider, Codex CLI, and OpenCode.
Uses tree-sitter AST for TypeScript/JavaScript with framework-aware passes for 9 substrates.
Offers MCP tools like retrieve, impact, call_chain, and community_overview.

Use cases of Graphify Ts

Cut token usage and latency on codebase questions by providing pre-compiled context to AI agents.
Review pull request diffs with structured blast-radius analysis and ranked review risks.
Explore unfamiliar codebases through architecture summaries, call chains, and dependency graphs.
Run multi-agent workflows across Claude Code, Codex, Copilot, Cursor, and Gemini with a single graph.

FAQ from Graphify Ts

What does Graphify Ts do that alternatives do not?

It builds a local knowledge graph once and compiles compact context packs on demand, so agents do not re-discover the codebase from scratch every session. Measured benchmarks show up to 5.28× fewer input tokens and 2.21× fewer tool-call turns.

What runtime dependencies are required?

Node.js 20 or later and npm. No API keys, no cloud services, and no external databases are required. The tool is installed as a single global npm package.

Where does your code data live?

Everything runs locally on your machine. Your code never leaves the laptop unless you explicitly invoke a model through a connected AI agent.

Which languages and frameworks does Graphify Ts support?

Deepest extraction is for TypeScript/JavaScript with framework-aware passes for Express, NestJS, Next.js, React Router, Redux Toolkit, Hono, Fastify, tRPC, and Prisma. Python, Ruby, Go, Java, and Rust use tree-sitter AST. C, Kotlin, C#, Scala, PHP, Swift, and Zig use a generic structural extractor.

How does Graphify Ts connect to AI agents?

It provides MCP integration for Claude Code, Cursor, Copilot CLI, and Gemini CLI. For Aider, Codex CLI, and OpenCode, it writes a context-pack-first profile. For Windsurf and others, you pipe the output of graphify-ts prompt directly to the agent.

よくある質問

What does Graphify Ts do that alternatives do not?

What runtime dependencies are required?

Node.js 20 or later and npm. No API keys, no cloud services, and no external databases are required. The tool is installed as a single global npm package.