mcp-server AGENTS.md

A repository instruction file that tells coding agents how to build, test, secure, and contribute to the WAVE MCP Server. MCP is a standard way for AI assistants to use connected tools.

In plain words
What is it for?
Guiding repository work such as running checks, following branch and commit rules, protecting secrets, and reporting security problems.
Why use it?
It gives agents the project rules they need before changing code or opening a pull request.

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/wave-av/mcp-server/agents-md
Clone the repo
git clone --depth 1 https://github.com/wave-av/mcp-server

Made for: Codex, OpenCode.

Per session 476 This file is loaded in full into every session.
When invoked 476 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 $0.00476 $0.00476
Opus 5 $0.00238 $0.00238
Sonnet 5 $0.00095 $0.00095
Haiku 4.5 $0.00048 $0.00048

Measured 2d ago against content hash 22d26cebaa4d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-server 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 2d 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 · 48 lines

What it actually says

AGENTS.md — wave-av/mcp-server

Agent contract for this repo. Inherits the org default (https://github.com/wave-av/.github/blob/main/AGENTS.md) and the repo-governance standard.

Build and test

See README.md for setup. Run the repo's lint / typecheck / test before opening a PR, and fix what you broke.

Rules

  • Branch and open a PR; never push to the default branch. All required gates must pass before merge.
  • No secrets in commits — secret-scan is a required gate and will block.
  • Conventional Commit titles; update CHANGELOG.md (Unreleased) for user-facing changes.
  • Match the existing code conventions; keep files focused (~200-500 lines).

Security

Report vulnerabilities via the Security Policy ([email protected]) — never in a public issue.

CONTENTS

@wave-av/mcp-server — WAVE MCP Server - Exposes WAVE streaming APIs as tools for AI agents

Top-level directories: scripts, src.

GUIDELINES

  • Every capability ships its four renderings (API + CLI + SDK + MCP); the API is the authority.
  • No secrets in git — credential values live in Doppler; keys arrive via ${DOPPLER:KEY} refs or dpg.mjs.
  • Public repos carry LICENSE in the same commit as first code.
  • Tests ship with the artifact in the same PR — no test, no ship; a green suite is not a live system.
  • Plans/runbooks live in governance/plans (or this repo's plans/ dir), never scattered.

Machine surface

version: "0.1"
budget_lines: 200
index:
  - family: permissions-contract
    path: PERMISSIONS.md
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. 2d ago First seen · 48 lines · 476 tokens per session scan A 22d26cebaa4d

Subscribe to this mod's changes

mcp-server AGENTS.md is an instructions file published in the GitHub repository wave-av/mcp-server (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 476 tokens to every session, about $0.0024 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.