Borrowing it
Nothing to install: this file belongs to NeoAIResearch/neo-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/NeoAIResearch/neo-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/NeoAIResearch/neo-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/neoairesearch/neo-mcp/claude-md)<a href="https://agentmods.dev/instructions/neoairesearch/neo-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/neoairesearch/neo-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/neoairesearch/neo-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/neoairesearch/neo-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.05993 | $0.05993 |
| Opus 5 | $0.02996 | $0.02996 |
| Sonnet 5 | $0.01199 | $0.01199 |
| Haiku 4.5 | $0.00599 | $0.00599 |
Grade C, and why
neo-mcp CLAUDE.md scanned grade C with 1 finding 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 3d 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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
- `get_file` with an absolute path outside workspace: remapped (not read directly). A compromised backend cannot read `/etc/passwd` or `~/.ssh/id_rsa`. How it starts
The opening of the file, as written. The whole thing — 354 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.
What this is
A Python MCP server that wraps the Neo ML backend (https://master.heyneo.com, or https://alpha.heyneo.com when staging is selected via ~/.neo/settings.json {"env": "staging"} or NEO_ENVIRONMENT=staging). It exposes 12 tools to Claude Code so users can submit ML/AI tasks, poll status, read output, control task lifecycle, and register third-party credentials (GitHub, HuggingFace, Anthropic, OpenRouter, OpenAI, AWS S3, Weights & Biases, Kaggle) — via stdio transport.
Current pip version: 0.5.13. Current npm version: 1.1.30.
Project structure
Each concern lives in its own top-level folder.
neo-mcp/
├── python/ # pip-installable MCP server (neo-mcp package)
│ ├── src/neo_mcp/
│ │ ├── server.py # MCP server — all 12 tools, single file
│ │ ├── system_info.py # exec_environment XML gatherer (OS/arch/CPU/RAM/shell/GPU/tools)
│ │ ├── integrations/ # GitHub/HF/Anthropic/OpenRouter/OpenAI/S3/W&B/Kaggle credentials
│ │ ├── oauth.py # OAuth 2.0 PKCE authorization server (HTTP mode)
│ │ ├── setup.py # setup wizard (neo-mcp setup)
│ │ ├── daemon.py # Python daemon (fallback — primary is npm daemon)
│ │ └── login.py # browser OAuth flow (neo-mcp login)
│ ├── tests/
│ │ ├── test_system.py # primary unit suite (366 tests, no key needed)
│ │ ├── test_auth.py # deployment ID policy tests
│ │ ├── test_server.py # legacy tests (stale — references old API)
│ │ └── test_connection.py # connectivity smoke test (needs key)
│ ├── scripts/start-daemon.sh # standalone daemon launcher (bash)
│ ├── pyproject.toml # package metadata + entry points
│ ├── requirements.txt # runtime deps
│ ├── Dockerfile # HTTP-mode container (used by CI → ECR)
│ └── DEPLOYMENT.md # Docker deployment guide
│
├── npm/ # npm daemon package (neo-mcp-daemon)
│ ├── src/
│ │ ├── daemon.ts # polling loop + command dispatch
│ │ ├── executor.ts # write_code, run_subprocess, etc. + path remapping
│ │ └── mcp-server.ts # MCP server with all 7 tool definitions
│ ├── bin/neo-mcp-daemon # CLI entry point
│ ├── package.json # npm package metadata (neo-mcp-daemon)
│ └── tsconfig.json
│
├── vscode_extension/ # VS Code/Cursor extension (TypeScript, own release cycle)
│
├── skills/ # Agent framework integrations
│ ├── README.md # index
│ ├── claude-code/SKILL.md # Claude Code /neo slash command
│ ├── neo-setup/SKILL.md # /neo-setup onboarding guide
│ ├── vercel/SKILL.md # Vercel AI SDK
│ ├── openai-agents/SKILL.md # OpenAI Agents SDK
│ └── langchain/SKILL.md # LangChain / LangGraph
│
├── docs/ # Shared documentation
│ ├── CLIENTS.md # Editor setup guide
│ ├── USAGE.md # Usage guide + workflows
│ ├── CONNECTORS.md # Claude.ai + ChatGPT web connector setup
│ └── WEB_CONNECTOR.md # Web connector implementation notes
│
├── .github/workflows/
│ └── publish-mcp.yml # CI: builds python/Dockerfile → ECR on push to main
├── README.md # Top-level overview + quick start
└── CLAUDE.md # This file
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.
- 3d ago First seen · 354 lines · 5,993 tokens per session scan C 5ae5c2f7ba63
neo-mcp CLAUDE.md is an instructions file published in the GitHub repository NeoAIResearch/neo-mcp (2 stars, last pushed 4d ago), licensed MIT. It adds 5,993 tokens to every session, about $0.0300 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-09.
Other instructions, from other repositories
spec-kit AGENTS.md
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.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
vscode buildNext.instructions.md
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).
langchain AGENTS.md
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.
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).