robinhood-mcp AGENTS.md

robinhood-mcp AGENTS.md is an instructions file for Codex, OpenCode from drasticstatic/robinhood-mcp. It costs 571 tokens per session, scanned A, original, MIT.

Project instructions for developing robinhood-mcp, a read-only MCP server that exposes research tools for Robinhood portfolio data. Robinhood is a financial service, and read-only means the server cannot place trades.

In plain words
What is it for?
Use them when installing, linting, testing, or starting robinhood-mcp, or when changing its Python tools and Robinhood data access.
Why use it?
They clarify the project's safety limits, setup, testing, authentication approach, and coding standards for agents working in the repository.

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/drasticstatic/robinhood-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/drasticstatic/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/drasticstatic/robinhood-mcp/agents-md.svg)](https://agentmods.dev/instructions/drasticstatic/robinhood-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/drasticstatic/robinhood-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/drasticstatic/robinhood-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 571 This file is loaded in full into every session.
When invoked 571 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 $0.00571 $0.00571
Opus 5 $0.00285 $0.00285
Sonnet 5 $0.00114 $0.00114
Haiku 4.5 $0.00057 $0.00057

Measured 3d ago against content hash ca64c3ea66c1, 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 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.

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 · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

AI Agent Configuration — robinhood-mcp Read by: Claude Code, Cursor, GitHub Copilot, and other AI coding assistants. See CLAUDE.md for Claude Code–specific rules.


Project Overview

robinhood-mcp is a read-only MCP server wrapping the robin_stocks Python library. Provides 12 research tools for Robinhood portfolio data. Strictly educational/research — no trading functionality exposed.

Upstream: Forked — tracked for voluntary comparison. Visibility: PRIVATE (working copy)


Tech Stack

Layer Technology
MCP server Python (FastMCP)
Robinhood API robin_stocks library
Auth TOTP 2FA support
Package manager pip
Testing pytest

Common Commands

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

# Run linting
ruff check .
ruff format --check .

# Run tests
pytest -v

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

# Start the server
robinhood-mcp

Coding Standards

  • Type hints on all functions
  • All robin_stocks calls wrapped with _safe_call() for consistent error handling
  • Lazy authentication — login happens on first tool call, not server startup
  • Tests use mocked responses — never use real credentials in tests
  • ruff for linting and formatting

Agent Boundaries

Do:

  • Keep this strictly read-only — research and portfolio visibility only
  • Use _safe_call() wrapper on all external API calls
  • Add tests alongside any new tool

Don't:

  • Expose any order_buy_*, order_sell_*, or cancel_*_order functions
  • Log or print Robinhood credentials
  • Store session tokens outside ~/.tokens/

Security Rules

  • ROBINHOOD_USERNAME, ROBINHOOD_PASSWORD, ROBINHOOD_TOTP_SECRET — environment variables only, never committed
  • Session tokens stored in ~/.tokens/ — gitignored
  • Never expose trading functions — read-only is a hard constraint, not a preference

Override System

Create AGENTS.override.md for temporary task-specific rules. Delete when done. Template: ~/code/my-template/AGENTS.override.md

Read the full file on GitHub · 94 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. 3d ago First seen · 94 lines · 571 tokens per session scan A ca64c3ea66c1

Subscribe to this mod's changes

robinhood-mcp AGENTS.md is an instructions file published in the GitHub repository drasticstatic/robinhood-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 571 tokens to every session, about $0.0029 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 2026-08-31.