Robinhood Mcp logo

Robinhood Mcp

Organization
aeonfun
robinhood-mcp

Read your Robinhood Agentic brokerage account via the Robinhood Trading MCP - portfolio, buying power, positions, and order history - and place a single operator-instructed trade. OAuth Connect via the dashboard MCP panel.

Overview

Publisheraeonfun
Repositoryaeon
Skill namerobinhood-mcp
Stars
771
Forks
280
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by aeonfun on GitHub. Read the source before you install it.

Installation

Install the Robinhood Mcp AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/aeonfun/aeon/tree/main/skills/robinhood-mcp
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/aeonfun/aeon.git /tmp/aeon
mkdir -p .claude/skills
cp -r /tmp/aeon/skills/robinhood-mcp .claude/skills/robinhood-mcp
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Robinhood Mcp in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Robinhood Mcp on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Robinhood Mcp is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

${var} — empty = portfolio report (read-only). orders[:N] = last N orders (default 10). trade:<instruction> = place one order, e.g. trade: buy $50 of AAPL — the only branch that writes. Anything else = treat as a question about the account and answer it read-only.

Access the operator's Robinhood Agentic Trading account through the Robinhood MCP server (agent.robinhood.com/mcp/trading). Trades execute in a dedicated Agentic brokerage account the operator authorized — real money, irreversible. The default posture is read-only reporting; an order is placed only when ${var} explicitly instructs it.

Detection & auth

The server is wired by the dashboard MCP panel's one-click Connect (OAuth; tokens stored as MCP_ROBINHOOD_TRADING_TOKEN + MCP_ROBINHOOD_TRADING_OAUTH, refreshed each run by scripts/mcp-oauth-refresh.sh). Its tools surface as mcp__robinhood-trading__* — discover them from the server; the tool descriptions are the source of truth, don't assume a fixed list.

  • No mcp__robinhood-trading__* tool callable → the server isn't connected (or its secrets are missing, in which case the workflow logged a ::warning:: and skipped MCP). Log RH_MCP_NOT_CONNECTED, notify once pointing the operator at the dashboard → MCP → Connect Robinhood Trading, and exit. Don't try to reach the API with curl — there is no static key.
  • Tools exist but return 401/invalid-token → the OAuth refresh failed (rotating refresh tokens need GH_SECRETS_PAT — see docs/mcp-oauth.md). Log RH_MCP_AUTH_STALE, notify the operator to re-connect the server once in the dashboard, and exit. Don't retry the same call more than twice.

Steps

1. Read the account

Whatever the branch, start with the reads — portfolio value, buying power, positions (symbol, quantity, cost basis, current value, unrealized P/L), and open orders. For orders[:N], pull order history and take the most recent N (default 10) with status, side, symbol, quantity/notional, and fill price.

2. Trade branch (only when ${var} starts with trade:)

Operator-initiated only — never trade on a scheduled/default run, and never invent an order.

  1. Parse the instruction. It must pin down side (buy/sell), symbol, and size (share quantity or dollar notional). If any of the three is missing or ambiguous ("buy some tech", "sell half-ish"), do not guess: log RH_MCP_ORDER_REFUSED, notify with what was missing, and exit.
  2. Sanity-check against the reads: selling more than the position holds, or buying beyond buying power → refuse the same way.
  3. Place the order as the final action of the run (fail-closed: everything else — reads, log prep — happens first, so a placement failure surfaces in this run). Use the order tool the server exposes; prefer its simplest market/notional form unless the instruction specifies a limit price.
  4. Capture the server's response verbatim (order id, status). If the tool call fails, log RH_MCP_ORDER_ERROR with the error body — never claim an order was placed without an order id back.

3. Notify

This skill is on-demand — deliver the result via ./notify -f <file> (ordinary Markdown), exactly one ./notify call per run (each call overwrites the .pending-<skill>.md file the chain artifact is captured from — a second ping would clobber the report):

  • Report branches: portfolio value + day change, buying power, a positions table, open orders, and one line of what stands out (concentration, a position moving hard). Keep it tight — signal, not a data dump.
  • Trade branch: the exact order placed (side, symbol, size, order id, status) — or, on refusal, exactly what was ambiguous and how to restate it. Severity success for a placed order, warn for a refusal.

4. Result record

This skill is read-only, so the workflow's read-only guard writes its ### robinhood-mcp log entry from your captured output; a self-written entry would be a duplicate. Don't append to memory/logs/ yourself - put this record in your final output; the workflow persists it to memory/logs/ and output/.chains/robinhood-mcp.md on your behalf after the run:

### robinhood-mcp
- Branch: portfolio | orders | trade
- Result: RH_MCP_OK | RH_MCP_ORDER_PLACED id=… | RH_MCP_ORDER_REFUSED reason=… | RH_MCP_NOT_CONNECTED | RH_MCP_AUTH_STALE | RH_MCP_ERROR
- Snapshot: value=$… bp=$… positions=N

Constraints

  • No unprompted trading, no advice. Report what the account holds; place only the order ${var} spells out. Never recommend a trade in the notify.
  • One order per run — a trade: instruction that describes multiple orders is refused, not partially executed.
  • Every figure in the notify traces to a tool response; never estimate fills or balances.
  • The operator is responsible for every order this agent places — when in doubt, refuse and say why.

Frequently asked questions

What does the Robinhood Mcp AI skill do?

Read your Robinhood Agentic brokerage account via the Robinhood Trading MCP - portfolio, buying power, positions, and order history - and place a single operator-instructed trade. OAuth Connect via the dashboard MCP panel.

Why use Robinhood Mcp on TypingMind?

Because you install it once and use it with any model. Robinhood Mcp is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Robinhood Mcp in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/aeonfun/aeon/tree/main/skills/robinhood-mcp. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Robinhood Mcp?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Robinhood Mcp?

As many as you like. As long as a model supports skills, you can use Robinhood Mcp with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Robinhood Mcp AI skill free?

Yes. It is published on GitHub by aeonfun under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇