rockfish-mcp: Instructions file for Claude Code

CLAUDE.md

rockfish-mcp CLAUDE.md is an instructions file for Claude Code from Rockfish-Data/rockfish-mcp. It costs 1,442 tokens per session, scanned A, original, MIT.

A set of Claude Code instructions for developing the Rockfish MCP server. It documents setup, locked Python dependencies, environment variables, and how to run the server.

In plain words
What is it for?
Use it when installing or developing the server, configuring Rockfish and optional Manta access, or starting it locally.
Why use it?
It gives developers the required Python version, virtual-environment steps, package source, and API settings needed to work on the project.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is Rockfish-Data/rockfish-mcp's own configuration. It tells Claude Code how to work on rockfish-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything rockfish-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Rockfish-Data/rockfish-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/Rockfish-Data/rockfish-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Rockfish-Data/rockfish-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.

agentmods badge for rockfish-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rockfish-data/rockfish-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/rockfish-data/rockfish-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/rockfish-data/rockfish-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/rockfish-data/rockfish-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.

agentmods 80×15 button for rockfish-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/rockfish-data/rockfish-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/rockfish-data/rockfish-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,442 This file is loaded in full into every session.
When invoked 1,442 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01442 $0.01442
Opus 5.5 $0.00577 $0.00577
Sonnet 5.5 $0.00288 $0.00288
Haiku 4.5 $0.00144 $0.00144

Measured 1mo ago against content hash a3feed9253f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rockfish-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 · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 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.

Development Commands

Installation and Setup

IMPORTANT: Dependencies are managed with uv and locked in uv.lock. .python-version pins the default Python (3.12). Newer Pythons should work, but Homebrew's Python 3.14 (linked against OpenSSL 4.0) currently crashes on import because the Rockfish SDK's Snowflake dependency still references the removed ssl.PROTOCOL_TLSv1; use a uv-managed or python.org build instead until that is fixed upstream.

# Create .venv and install the exact locked versions, including dev tools (black, isort, pytest)
uv sync

# Run commands in the project environment without activating it
uv run pytest tests/test_manta_client.py tests/test_manta_tools.py
uv run rockfish-mcp

After changing dependencies in pyproject.toml, refresh the lock with uv lock and commit uv.lock.

Important: The Rockfish SDK is hosted at https://packages.rockfish.ai, configured as a find-links source under [tool.uv] in pyproject.toml. There is no requirements.txt; uv.lock is the source of truth.

Environment Setup

Required in a .env file at the project root:

  • ROCKFISH_API_KEY: API key (required)
  • ROCKFISH_API_URL: Defaults to https://api.rockfish.ai
  • ROCKFISH_ORGANIZATION_ID: Falls back to the account default if unset
  • ROCKFISH_PROJECT_ID: Falls back to the account default if unset
  • MANTA_API_URL: Enables Manta tools when set (e.g. https://manta.rockfish.ai)
cp .env.example .env

Running the Server

python -m rockfish_mcp.server
# or
rockfish-mcp

Code Formatting

isort src/rockfish_mcp/ && black src/rockfish_mcp/

# Check only
isort --check-only src/rockfish_mcp/ && black --check src/rockfish_mcp/

Running Tests

The test suite has two tiers:

Unit tests — no credentials required, run locally:

pytest tests/test_manta_client.py tests/test_manta_tools.py

Read the full file on GitHub · 127 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.

  1. 1mo ago Changed · +105 tokens per session a3feed9253f4
  2. 2mo ago First seen · 127 lines · 1,337 tokens per session scan A 6c8dd24f6bae

Subscribe to this mod's changes

rockfish-mcp CLAUDE.md is an instructions file published in the GitHub repository Rockfish-Data/rockfish-mcp (0 stars, last pushed 26d ago), licensed MIT. It adds 1,442 tokens to every session, about $0.0058 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.

Related

rockfish-mcp CLAUDE.md compared with instructions from other repositories

rockfish-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
rockfish-mcp CLAUDE.mdRockfish-Data/rockfish-mcpInstructions file026d agoMITA1,442Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283ktodayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot