What is tv-mcp AGENTS.md?

Instructions for connecting an AI agent to Trading Volatility, a service that provides read-only options-market data such as dealer positioning, volatility skew, and expected moves. It uses the Model Context Protocol (MCP), a standard way for agents to call external tools.

Retrieving options market structure, checking gamma and volatility levels, comparing tickers, and finding ranked trade setups through the Trading Volatility API.

It explains how to connect, authenticate, discover available data, and choose the right query before requesting market information. It also makes clear that the service does not place trades.

How tradingvolatility/tv-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to tradingvolatility/tv-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/tradingvolatility/tv-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/tradingvolatility/tv-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/tradingvolatility/tv-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/tradingvolatility/tv-mcp/agents-md)

Your own site

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

Per session 740 This file is loaded in full into every session.

When invoked 740 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	$0.00740	$0.00740
Opus 5.5	$0.00296	$0.00296
Sonnet 5.5	$0.00148	$0.00148
Haiku 4.5	$0.00074	$0.00074

Measured 2mo ago against content hash b2eb8116e46d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tv-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 2mo 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 · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trading Volatility MCP — for AI agents

This is a Model Context Protocol server that gives agents read-only access to Trading Volatility options market-structure data: GEX, gamma flip levels, dealer positioning, volatility skew, max pain, expected-move levels, options volume, and cross-ticker ranked trade setups.

It is a stateless passthrough over the public v2 API — it discovers and retrieves data, and never places orders or takes payments.

Connect

Endpoint: POST <this-server>/mcp — Streamable HTTP + SSE (standard MCP transport).
Auth: send your Trading Volatility API key as Authorization: Bearer <key> (X-Api-Key: <key> also works).
No key? The demo tickers — AAPL, VIX, KO, META, AMZN, XOM, GM, MCD — work without one.
Local: uvx tv-mcp runs the same server over stdio.

First call

Call list_capabilities first. It returns the v2 /llm-spec manifest — the full set of endpoints, metrics, expirations, regimes, and screener names — so you can self-orient before querying. Call get_auth_status to see whether you're in keyed or demo mode.

Tools

Tool	Returns
`list_capabilities`	The v2 capability manifest (`/llm-spec`) — call first
`get_auth_status`	Whether you're in keyed or demo mode
`get_ticker_state`	Canonical compact state snapshot for a ticker
`explain_ticker`	Deterministic narrative interpretation of the regime
`get_market_structure`	Headline signal, regime, expected behavior, levels
`get_signals`	Current setup/positioning signals
`get_levels`	Key levels (json / tradingview / tos)
`get_series`	Historical daily series for selected metrics over a window
`get_gamma_curve`	Gamma strike curve (per expiration, optionally realtime)
`get_gamma_by_expiration`	Gamma decomposition by expiration bucket
`get_gex_by_strike`	Net GEX strike curve with call/put contributions
`get_options_volume`	Options volume by strike for an expiration
`rank_top_setups`	Cross-ticker opportunity ranking, with filters
`run_screener`	A named thesis preset over the ranking
`rank_income_setups`	Cross-ticker covered-call / cash-secured-put ranking, with filters
`get_trade_setup`	Compact agent-oriented trade setup for one ticker

Read the full file on GitHub · 56 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.

2mo ago First seen · 56 lines · 740 tokens per session scan A b2eb8116e46d

Subscribe to this mod's changes

tv-mcp AGENTS.md is an instructions file published in the GitHub repository tradingvolatility/tv-mcp (1 stars, last pushed 4mo ago), licensed MIT. It adds 740 tokens to every session, about $0.0030 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 2026-08-31.

Finance and fintech

tv-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
tv-mcp AGENTS.mdtradingvolatility/tv-mcp	Instructions file	1	4mo ago	MIT	A	740	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

tv-mcp: Instructions file for Codex