robinhood-mcp AGENTS.md

robinhood-mcp AGENTS.md is an instructions file for Codex, OpenCode from verygoodplugins/robinhood-mcp. It costs 3,412 tokens per session, scanned A, original, MIT.

A contributor guide for robinhood-mcp, a server that lets AI assistants read Robinhood portfolio and market information. MCP (Model Context Protocol) is a standard way for assistants to call tools; this project is strictly read-only and cannot place or cancel trades.

In plain words
What is it for?
Use it when modifying the server, its Robinhood data tools, account selection, tests, or development setup.
Why use it?
It prevents changes from accidentally adding account-changing operations and explains how the project is built and installed.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/verygoodplugins/robinhood-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/verygoodplugins/robinhood-mcp

Made for: Codex, OpenCode.

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 robinhood-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/verygoodplugins/robinhood-mcp/agents-md.svg)](https://agentmods.dev/instructions/verygoodplugins/robinhood-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/verygoodplugins/robinhood-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/verygoodplugins/robinhood-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,412 This file is loaded in full into every session.
When invoked 3,412 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.03412 $0.03412
Opus 5 $0.01706 $0.01706
Sonnet 5 $0.00682 $0.00682
Haiku 4.5 $0.00341 $0.00341

Measured 4d ago against content hash 0d8c95373a35, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

robinhood-mcp AGENTS.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 4d 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.

AGENTS.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to coding agents (Claude Code, Cursor, Codex, etc.) when working with this repository. It is the single source of truth; CLAUDE.md imports it via @AGENTS.md.

Project Overview

robinhood-mcp is a read-only MCP (Model Context Protocol) server that wraps the robin_stocks Python library to expose Robinhood portfolio data as research tools for AI assistants. It is strictly a research/educational tool — no trading functionality is exposed.

Core purpose:

  • Translate MCP tool calls into robin_stocks Robinhood API requests over stdio
  • Provide read-only portfolio, quote, fundamentals, news, and order-history research
  • Support multi-account Robinhood logins (taxable, IRA, etc.) via optional account selection

Read-only is a hard invariant

The server never exposes order placement, cancellation, or any account-modifying call. There are no order_buy_*, order_sell_*, or cancel_* tools, and none should ever be added. Every tool delegates to read-only robin_stocks endpoints (rh.profiles.*, rh.stocks.*, rh.account.* getters, rh.orders.get_all_stock_orders, rh.options.get_open_option_positions). When adding a tool, preserve this invariant; the order-history tool explicitly documents "Read-only — this never places or cancels orders" (tools.py:639).

Build & Development

# Install with dev dependencies (editable)
pip install -e ".[dev]"

# Lint and format-check (ruff; line-length 100, target py311)
ruff check .
ruff format --check .

# Run tests
pytest -v

# Run tests with coverage
pytest --cov=src --cov-report=html

# Smoke test (import + server instantiation + entry point)
./scripts/smoke.sh

# Run the MCP server (stdio mode)
robinhood-mcp

robinhood-mcp is the console-script entry point, wired to robinhood_mcp.server:main (pyproject.toml:36-37). Python >= 3.11 is required (pyproject.toml:11). Runtime dependencies: fastmcp, robin_stocks, python-dotenv, pyotp (pyproject.toml:21-26).

Read the full file on GitHub · 179 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. 4d ago First seen · 179 lines · 3,412 tokens per session scan A 0d8c95373a35

Subscribe to this mod's changes

robinhood-mcp AGENTS.md is an instructions file published in the GitHub repository verygoodplugins/robinhood-mcp (39 stars, last pushed 1mo ago), licensed MIT. It adds 3,412 tokens to every session, about $0.0171 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.