What is alphagenome-mcp CLAUDE.md?

Repository instructions for AlphaGenome MCP, a server that connects coding agents to Google DeepMind’s AlphaGenome AI for genomic variant analysis. MCP is a standard way for an AI tool to communicate with software.

Use it when installing, building, formatting, linting, type-checking, testing, running, or understanding the architecture of this TypeScript and Python project.

It gives contributors one place to find the project overview, required dependencies, development commands, and operating details.

How taehojo/alphagenome-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to taehojo/alphagenome-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.

Copy the file

curl -O https://raw.githubusercontent.com/taehojo/alphagenome-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/taehojo/alphagenome-mcp

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/taehojo/alphagenome-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/taehojo/alphagenome-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/taehojo/alphagenome-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/taehojo/alphagenome-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/taehojo/alphagenome-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/taehojo/alphagenome-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,335 This file is loaded in full into every session.

When invoked 2,335 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.02335	$0.02335
Opus 5.5	$0.00934	$0.00934
Sonnet 5.5	$0.00467	$0.00467
Haiku 4.5	$0.00233	$0.00233

Measured 1mo ago against content hash 9b7ede8051d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

alphagenome-mcp 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 1mo 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.

CLAUDE.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 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

AlphaGenome MCP (Model Context Protocol) Server: AlphaGenome as a tool for Claude agents. The agent turns a researcher's question into an analysis; the server answers single-nucleotide variants from the precomputed AlphaGenome Atlas and indels and other variants the Atlas cannot precompute with live inference, chooses between the two automatically, and states the source on every result.

Real API Integration: Uses the AlphaGenome Python SDK through a Python bridge. Nothing is mocked.

Development Commands

Building and Testing

# Install dependencies
npm install

# Build TypeScript
npm run build

# Watch mode (development)
npm run dev

# Run linter
npm run lint
npm run lint:fix

# Format code
npm run format
npm run format:check

# Type check without building
npm run typecheck

# Build, then run the TypeScript unit tests (no API key needed)
npm test

# Python unit tests for the shared summarizer (numpy and pandas only)
npm run test:python

# Regenerate docs/API.md from src/tools.ts (CI fails if it is out of date)
npm run docs:api

Running Locally

# Run with your AlphaGenome API key
ALPHAGENOME_API_KEY=your-key-here node build/index.js

# Or provide via command-line argument
node build/index.js --api-key your-key-here

# The server communicates via stdio (MCP protocol)
# Output to stderr is for logging, stdout is for MCP messages

Architecture

Core Components

src/index.ts - Main MCP server entry point
- Handles MCP protocol communication
- Routes tool calls to appropriate handlers
- Error handling and formatting
src/alphagenome-client.ts - API client
- Spawns the Python bridge once per call; the API key travels on stdin, never on the command line
- Timeout per call (ALPHAGENOME_TIMEOUT_MS, default 180000): the process is killed and a NetworkError is raised
- Interpreter choice: ALPHAGENOME_PYTHON pins one; otherwise python3, then python
- Reads the JSON on stdout before judging the exit code, and maps error_type to typed errors
- Atlas methods; the scorer list is cached for the session

Read the full file on GitHub · 196 lines

Changes

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.

1mo ago Changed · +1 lines · +36 tokens per session 9b7ede8051d1
1mo ago Changed · +40 lines · +1,347 tokens per session f1ce163fc775
2mo ago First seen · 155 lines · 952 tokens per session scan A 8319bf446611

Subscribe to this mod's changes

alphagenome-mcp CLAUDE.md is an instructions file published in the GitHub repository taehojo/alphagenome-mcp (2 stars, last pushed 4d ago), licensed MIT. It adds 2,335 tokens to every session, about $0.0093 per session on Opus 5.5. 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 2026-08-31.

Data and AI Scientific

alphagenome-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
alphagenome-mcp CLAUDE.mdtaehojo/alphagenome-mcp	Instructions file	2	4d ago	MIT	A	2,335	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

alphagenome-mcp: Instructions file for Claude Code