yahoo-finance-mcp: Instructions file for Codex

AGENTS.md

yahoo-finance-mcp AGENTS.md is an instructions file for Codex, OpenCode from danishashko/yahoo-finance-mcp. It costs 967 tokens per session, scanned A, original, MIT.

A repository instruction file that tells coding agents how the yahoo-finance-mcp project is organised and what rules its code must follow. It covers files, implementation patterns, checks, and release procedures.

In plain words
What is it for?
Use it as guidance when developing, testing, or releasing this MCP server and its command-line wrapper.
Why use it?
It gives an agent the project-specific constraints it needs before changing code. This reduces the risk of breaking required interfaces or skipping release checks.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is danishashko/yahoo-finance-mcp's own configuration. It tells Codex and OpenCode how to work on yahoo-finance-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything yahoo-finance-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to danishashko/yahoo-finance-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/danishashko/yahoo-finance-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/danishashko/yahoo-finance-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 yahoo-finance-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/danishashko/yahoo-finance-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/danishashko/yahoo-finance-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/danishashko/yahoo-finance-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/danishashko/yahoo-finance-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.

agentmods 80×15 button for yahoo-finance-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/danishashko/yahoo-finance-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/danishashko/yahoo-finance-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 967 This file is loaded in full into every session.
When invoked 967 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00967 $0.00967
Opus 5.5 $0.00387 $0.00387
Sonnet 5.5 $0.00193 $0.00193
Haiku 4.5 $0.00097 $0.00097

Measured yesterday against content hash 8e2ea91140af, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

yahoo-finance-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 yesterday.

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 · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Rules for an agent changing this repo. For what the server does, read llms.txt and README.md.

Layout

  • yahoo_finance_mcp.py is the whole server: MCPServer from the mcp Python SDK v2, data from yfinance.
  • bin/cli.js is the npx wrapper. It builds a venv and reinstalls dependencies whenever requirements.txt changes (it hashes the file).
  • server.json is the MCP registry manifest. package.json is the npm package.

Invariants

  • Tools are plain sync defs decorated @mcp.tool(structured_output=False, ...) then @structured(<Model>Out). SDK v2 runs a sync tool on a worker thread, so one slow call does not stall other HTTP clients. Never make a tool async def without awaiting real async I/O: an async tool runs on the event loop.
  • Every tool carries annotations (title, readOnlyHint, destructiveHint, idempotentHint, openWorldHint) and a response_format parameter.
  • Each tool builds its text in _md() and its JSON in _js() and returns _respond(response_format, _md, _js). _js() always runs: its payload is the structured content, so it must match the tool's <Model>Out in the STRUCTURED OUTPUT section. A new field goes in both. _publish_output_schemas() publishes the schemas; they are not enforced at call time, so the release check enforces them.
  • JSON output goes through _json(), never json.dumps directly. yfinance returns NaN for missing figures and bare NaN is invalid JSON; _json() also turns the Markdown placeholder "N/A" into null.
  • Oversized output goes through truncate_response (markdown) or truncate_json_response / _fit_records (JSON). Never return more than CHARACTER_LIMIT. Prefer trimming to the useful rows (_fit_records, the options chain's nearest strikes) over truncate_json_response, which fails a JSON request.
  • Failures raise ToolError (via _error(), which also recognises Yahoo rate-limiting), so the client gets isError: true. Never return an error as plain text. "No data for this symbol" is a normal answer, not an error.
  • A tool that reads .info calls _require_known(): yfinance does not raise for an unknown symbol, it returns empty fields.
  • _norm_ticker() rewrites class shares (BRK.B, BRK/B) to Yahoo's BRK-B. Every ticker argument goes through it.
  • Use make_ticker() and _get_session() so every call shares one browser-impersonating session.
  • The shared session impersonates safari, not chrome. On curl_cffi 0.17 (required by yfinance 1.8) the chrome and firefox profiles stall the first request on every new thread, against any host, so parallel bursts queued up for ~8s. safari and edge do not. Do not switch back without re-running the concurrency check.
  • Concurrency check before a release: over --http, fire three bursts of 8 parallel get_stock_quote calls. Every burst, including the first and one after 20 seconds idle, should finish in about 1 second.

Read the full file on GitHub · 36 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. yesterday First seen · 36 lines · 967 tokens per session scan A 8e2ea91140af

Subscribe to this mod's changes

yahoo-finance-mcp AGENTS.md is an instructions file published in the GitHub repository danishashko/yahoo-finance-mcp (24 stars, last pushed yesterday), licensed MIT. It adds 967 tokens to every session, about $0.0039 per session on Opus 5.5. 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 2026-11-07.

Related

yahoo-finance-mcp AGENTS.md compared with instructions from other repositories

yahoo-finance-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
yahoo-finance-mcp AGENTS.mddanishashko/yahoo-finance-mcpInstructions file24yesterdayMITA967Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot