What is battlegrid-mcp AGENTS.md?

Machine-readable connection instructions for the BattleGrid MCP server, including its protocol, connection methods, authentication, and API-key format. MCP is a standard for connecting AI agents to tools.

Use them to configure a local npm connection or remote connection to BattleGrid and determine the required access permissions.

They tell an agent exactly how to find and authenticate with BattleGrid instead of relying on guessed connection details.

How playbattlegrid/battlegrid-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to playbattlegrid/battlegrid-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/playbattlegrid/battlegrid-mcp/main/AGENTS.md

Clone the repo

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

Your own site

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

Per session 2,169 This file is loaded in full into every session.

When invoked 2,169 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	$0.02169	$0.02169
Opus 5.5	$0.00868	$0.00868
Sonnet 5.5	$0.00434	$0.00434
Haiku 4.5	$0.00217	$0.00217

Measured 7d ago against content hash d9103ed3e188, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

battlegrid-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 7d 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 · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — BattleGrid MCP Server

Machine-readable agent discovery file for @battlegrid/mcp-server (thin stdio proxy to BattleGrid's remote MCP server).

Platform

Field	Value
Name	BattleGrid
Website	https://battlegrid.trade
Protocol	Model Context Protocol (MCP)
Transport	stdio (npm package), streamable-http (remote)
Package version	The proxy's own build identity. It makes no claim about the server's contract and never needs to move when the contract does.
Contract version	Relayed from the upstream handshake on every connection, so it is always the contract you will actually reach. Read it from the stdio handshake (`battlegrid@<contract>`, printed to stderr at startup) or `GET https://mcp.battlegrid.trade/mcp/version`. The two versions differ by design — that is not drift.

Authentication

Field	Value
Method	OAuth 2.1 with Dynamic Client Registration (default, remote) / API key (fallback — headless, no remote transport, or multi-account). Authentication is a property of the PATH, not of the client.
Format	`bg_live_*` (API key path only)
Header	`Authorization: Bearer <API_KEY>` (API key path only; OAuth carries its own token)
Obtain	OAuth needs nothing to obtain — authorize in the browser. For a key: https://battlegrid.trade → Profile → MCP tab
Scopes	`mcp:read` (discovery + non-financial config writes), `mcp:wager` (financial actions)

Connection

Option A: Remote / streamable-http over OAuth — the default

URL: https://mcp.battlegrid.trade/mcp

Register the URL on a streamable-http transport and authorize: the client registers itself by Dynamic Client Registration and BattleGrid's consent page opens in the browser. No npm package, no API key. Grants are listed and revocable under Profile → MCP → OAuth Sessions.

Option B: API key — headless, no remote transport, or multi-account

Use a key when the runtime cannot open a browser to consent, when the client speaks stdio only, or when one process drives several BattleGrid accounts (OAuth grants one account each).

Read the full file on GitHub · 105 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.

7d ago Changed · +2 tokens per session d9103ed3e188
17d ago Changed · +1 lines · +52 tokens per session 66a379382a27
20d ago Changed · +35 tokens per session 577e40f99191
21d ago Changed · -75 tokens per session 40c7043796db
25d ago Changed · -8 tokens per session ceaae1a524de
27d ago Changed · +35 tokens per session d9b151f2403d
1mo ago Changed · +1 lines · +63 tokens per session f97307490b95
1mo ago Changed · +2 lines · +104 tokens per session f01b84fffaf4
2mo ago Changed · +9 lines · +255 tokens per session 53d985d08108
2mo ago First seen · 92 lines · 1,706 tokens per session scan A a88d7ed0e075

Subscribe to this mod's changes

battlegrid-mcp AGENTS.md is an instructions file published in the GitHub repository playbattlegrid/battlegrid-mcp (0 stars, last pushed today), licensed MIT. It adds 2,169 tokens to every session, about $0.0087 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.

battlegrid-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
battlegrid-mcp AGENTS.mdplaybattlegrid/battlegrid-mcp	Instructions file	0	today	MIT	A	2,169	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

battlegrid-mcp: Instructions file for Codex