Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/diffbot/mcp-code-graph/claude-mdgit clone --depth 1 https://github.com/diffbot/mcp-code-graphWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00482 | $0.00482 |
| Opus 5 | $0.00241 | $0.00241 |
| Sonnet 5 | $0.00096 | $0.00096 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
mcp-code-graph CLAUDE.md scanned grade A with 0 findings 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 2d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
This is a Model Context Protocol (MCP) server that provides seamless interaction with CodeGPT's Code Graphs. The server enables semantic code search, dependency analysis, and code retrieval across repository knowledge graphs.
Development Commands
# Build the project
npm run build
# Build and watch for changes during development
npm run watch
# Test the MCP server locally
node dist/index.js
# Debug MCP server with wrapper
node debug-mcp.js
Architecture
Core Components
- src/index.ts: Main MCP server implementation with all tool definitions
- debug-mcp.js: Wrapper script for debugging ES module compatibility
- dist/: Compiled JavaScript output (generated by TypeScript)
MCP Tools Implemented
The server implements 6 main tools for interacting with CodeGPT's knowledge graphs:
- list-graphs: Lists available repository graphs (only when CODEGPT_GRAPH_ID not set)
- get-code: Retrieves complete code implementation of functionalities
- find-direct-connections: Explores immediate relationships in the code graph
- nodes-semantic-search: Semantic search for code functionalities
- docs-semantic-search: Semantic search through documentation
- get-usage-dependency-links: Deep dependency analysis for impact assessment
Configuration
The server uses environment variables for configuration:
CODEGPT_API_KEY(required): API key for CodeGPT serviceCODEGPT_ORG_ID(optional): Organization IDCODEGPT_GRAPH_ID(optional): Specific graph ID
Arguments can also be passed via command line in order: API_KEY, ORG_ID, GRAPH_ID.
Key Implementation Details
- Uses
@modelcontextprotocol/sdkfor MCP protocol implementation - Implements dynamic schema generation based on environment variables
- Includes extensive error handling and logging
- TypeScript with ES2022 target and NodeNext modules
- Communicates with CodeGPT API at
https://api-mcp.codegpt.co/api/v1
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.
- 2d ago First seen · 63 lines · 482 tokens per session scan A 52a015f36771
mcp-code-graph CLAUDE.md is an instructions file published in the GitHub repository diffbot/mcp-code-graph (402 stars, last pushed 9mo ago), licensed MIT. It adds 482 tokens to every session, about $0.0024 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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.
buildNext
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain 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.