What is mm-ibkr-mcp AGENTS.md?

A set of instructions for a code repository that connects an AI agent to Interactive Brokers, an online brokerage platform. It covers account monitoring, order previews, trade execution, Telegram approvals, and stored trade intents.

It is for developing, testing, and running the mm-ibkr-mcp server, which reads account data, evaluates orders, tracks trade requests, and executes approved trades through IB Gateway or TWS.

It gives the agent a defined process for handling trades when real money may be at risk, including required checks and user confirmation.

How MrRolie/mm-ibkr-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to MrRolie/mm-ibkr-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/MrRolie/mm-ibkr-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/MrRolie/mm-ibkr-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/mrrolie/mm-ibkr-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/mrrolie/mm-ibkr-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/mrrolie/mm-ibkr-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/mrrolie/mm-ibkr-mcp/agents-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/mrrolie/mm-ibkr-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/mrrolie/mm-ibkr-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 939 This file is loaded in full into every session.

When invoked 939 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	$0.00939	$0.00939
Opus 5	$0.00469	$0.00469
Sonnet 5	$0.00188	$0.00188
Haiku 4.5	$0.00094	$0.00094

Measured 9d ago against content hash 344bb3d8948c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mm-ibkr-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 9d 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 · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md – mm-ibkr-mcp

Purpose

Canonical Interactive Brokers MCP repo for agent-driven account monitoring, order preview, trade execution, Telegram approvals, and durable trade-intent tracking.

The repo assumes IB Gateway or TWS is already running on the user's machine. It does not manage the broker process.

Stack

Python 3.11+
uv
MCP SDK
ib-insync
Pydantic v2
SQLite

Commands

Task	Command
Install	`uv sync --group dev`
Test (non-integration)	`uv run pytest -m "not integration" -q`
Test (all)	`uv run pytest`
Compile check	`uv run python -m compileall -q ibkr_core mcp_server trade_core tests`
MCP server	`uv run ibkr-mcp`

Safety Rules

Real capital is at risk in this repo. It is imperative that the agent follows all skill directives exactly, especially the ibkr-place-order and ibkr-evaluate-order skills. Do not skip steps, skip questions, or short-circuit skill workflows for any reason.

Critical confirmation rule: When any skill — particularly ibkr-place-order Phase 1 — requires the agent to present state to the user and confirm before proceeding, the agent MUST use the question tool. Presenting a status summary in plain text and ending the turn is a policy violation. See the Confirmation Policy section below.

Safe defaults stay on: orders_enabled=false, dry_run=true.
Never bypass control.json safety controls. Use admin tools (requires MCP_ENABLE_ADMIN_TOOLS=true in .env) to programmatically adjust orders_enabled or dry_run if requested by user.
Treat MCP_ORDER_APPROVAL_MODE=telegram as the default launch mode.
Telegram approval requests (request_trade_approval, request_trade_intent_approval, request_environment_change) block synchronously. Do not manually poll for their completion; simply wait for the tool to return the final approved, denied, or expired status.
Ensure approval_id is always passed from the approval tools to their corresponding execution tools.
Preserve UTC ISO 8601 timestamps for persisted audit and order history.
Keep order flows preview-first when adding or changing execution behavior.

Read the full file on GitHub · 75 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.

9d ago First seen · 75 lines · 939 tokens per session scan A 344bb3d8948c

Subscribe to this mod's changes

mm-ibkr-mcp AGENTS.md is an instructions file published in the GitHub repository MrRolie/mm-ibkr-mcp (0 stars, last pushed 27d ago), licensed MIT. It adds 939 tokens to every session, about $0.0047 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.

Finance and fintech

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

mm-ibkr-mcp: Instructions file for Codex