stock-intelligence-mcp AGENTS.md

stock-intelligence-mcp AGENTS.md is an instructions file for Codex, OpenCode from thinkchainai/stock-intelligence-mcp. It costs 1,947 tokens per session, scanned A, original, MIT.

Instructions for a stock-market data MCP server with charts and text-based data tools.

In plain words
What is it for?
Use it to retrieve stock quotes, price history, and other supported market data, or to display that information through the server's chart views.
Why use it?
They clarify when an agent should show an interactive chart and when it should return figures as text, avoiding the wrong type of response.

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/thinkchainai/stock-intelligence-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/thinkchainai/stock-intelligence-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 stock-intelligence-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/thinkchainai/stock-intelligence-mcp/agents-md.svg)](https://agentmods.dev/instructions/thinkchainai/stock-intelligence-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/thinkchainai/stock-intelligence-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/thinkchainai/stock-intelligence-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,947 This file is loaded in full into every session.
When invoked 1,947 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 $0.01947 $0.01947
Opus 5 $0.00974 $0.00974
Sonnet 5 $0.00389 $0.00389
Haiku 4.5 $0.00195 $0.00195

Measured 4d ago against content hash 0f7ff710dac8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

stock-intelligence-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 · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stock Intelligence MCP — Agent Instructions

What This Is

An MCP App Server for stock market data with AI-driven dynamic charting. 10 tools: 1 interactive charting tool (stock_app with 7 views and inline controls), 7 inline data tools (for text responses), and 2 utility tools. Built with FastMCP (Python). All data from Financial Modeling Prep (FMP) free tier (250 calls/day).

Key Architectural Decision: Two Modes

Visual modestock_app is the single charting tool. It has meta={"ui": {"resourceUri": APP_RESOURCE_URI}} which opens the MCP App. The AI picks the view based on the user's question. The chart renders with inline controls (period, chart type, statement type) so users can adjust without a new AI call.

Inline mode — 7 data tools (stock_quote, stock_price_history, etc.) return structured data for text responses. No meta, no UI. The AI formats the data in its response.

When to use which:

  • User says "show me", "chart", "visualize" → stock_app
  • User says "what's the price", "tell me", "how much" → data tool
  • User asks for numbers then says "chart that" → stock_app with same params

Architecture

src/stock_intelligence/
├── __init__.py        # Package init — exports get_app_html()
├── server.py          # FastMCP server — 10 tools + MCP App resource
├── core/
│   ├── views.py       # View renderers + inline data functions (public API)
│   ├── scoring.py     # Quote summarization, number formatting
│   └── clients/
│       └── fmp.py     # FMP API client — free tier endpoints only
└── ui/
    └── app.html       # Interactive chart renderer — canvas-based, zero deps, inline controls

stock_app Views & Parameters

stock_app(
    symbol="AAPL",       # Stock ticker. Ignored for market view.
    view="chart",        # chart|quote|financials|earnings|analyst|valuation|market
    period="6m",         # Chart view: 1m|3m|6m|1y|2y|5y
    chart_type="",       # Override rendering. Leave empty for best default.
    statement="income",  # Financials view: income|balance|cashflow
    fiscal_period="quarter",  # Financials view: quarter|annual
)

Read the full file on GitHub · 159 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 · 159 lines · 1,947 tokens per session scan A 0f7ff710dac8

Subscribe to this mod's changes

stock-intelligence-mcp AGENTS.md is an instructions file published in the GitHub repository thinkchainai/stock-intelligence-mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 1,947 tokens to every session, about $0.0097 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.

Related

Other instructions, from other repositories