mcp-a2a-bridge AGENTS.md

mcp-a2a-bridge AGENTS.md is an instructions file for Codex, OpenCode from TonPC64/mcp-a2a-bridge. It costs 543 tokens per session, scanned A, original, MIT.

Project instructions for `mcp-a2a-bridge`, a Python bridge between MCP tools and A2A agents. A2A is a protocol for AI agents to communicate with one another; the project also has an optional web dashboard.

In plain words
What is it for?
Installing and running the bridge in MCP-only or dashboard mode, connecting it to A2A agents, and contributing changes with tests and security checks.
Why use it?
They explain which setup to choose, which parts are optional, and how to build and test the bridge safely.

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/tonpc64/mcp-a2a-bridge/agents-md
Clone the repo
git clone --depth 1 https://github.com/TonPC64/mcp-a2a-bridge

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 mcp-a2a-bridge AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tonpc64/mcp-a2a-bridge/agents-md.svg)](https://agentmods.dev/instructions/tonpc64/mcp-a2a-bridge/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/tonpc64/mcp-a2a-bridge/agents-md"><img src="https://agentmods.dev/badge/instructions/tonpc64/mcp-a2a-bridge/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 543 This file is loaded in full into every session.
When invoked 543 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 5.1 $0.00543 $0.00543
Opus 5 $0.00271 $0.00271
Sonnet 5 $0.00109 $0.00109
Haiku 4.5 $0.00054 $0.00054

Measured 4d ago against content hash e89426c3e402, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

mcp-a2a-bridge 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 · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI README

This file is the fast-start guide for coding agents working on mcp-a2a-bridge. Read it before changing code, then read the relevant skill:

  • skills/setup/SKILL.md — install and run MCP-only or MCP + dashboard.
  • skills/contribute/SKILL.md — branch, test, security review, commit, and PR workflow.

Project map

  • src/mcp_a2a_bridge/ — core MCP bridge, A2A client, registry, activity store, optional dashboard backend.
  • examples/copilot_a2a_agent/ — optional Copilot A2A server example.
  • dashboard/ — optional React/Vite dashboard frontend.
  • tests/ — Python tests, including integration coverage.
  • .github/workflows/ci.yml — CI for Python and dashboard.

Choose a setup

MCP-only (no dashboard runtime or Node/npm):

uv venv --python 3.11
uv pip install -e .
uv run mcp-a2a-bridge

MCP + dashboard:

uv venv --python 3.11
uv pip install -e ".[dashboard]"
npm --prefix dashboard ci
npm --prefix dashboard run build
uv run mcp-a2a-bridge-dashboard

Set A2A_BRIDGE_DASHBOARD=1 on bridge processes whose activity should appear in the dashboard. The dashboard defaults to 127.0.0.1:9100. A non-loopback bind without a token is for trusted LANs only; use a strong A2A_BRIDGE_DASHBOARD_TOKEN, TLS, and network controls for protected access. Never expose the dashboard directly to the public internet.

For frontend-only screenshots, run npm --prefix dashboard ci then npm --prefix dashboard run dev:mock -- --host 0.0.0.0. This opt-in mode uses local mock snapshots instead of the dashboard API/SSE; normal builds stay live.

Agent rules

  1. Read AGENTS.md and the relevant skill before editing.
  2. Preserve MCP-only installs: dashboard dependencies belong in the dashboard extra.
  3. Do not commit credentials, local registry files, .venv, node_modules, or generated screenshots.
  4. Prefer small, tested changes; preserve existing APIs and SSE contracts.
  5. Run the verification commands in skills/contribute/SKILL.md before reporting completion.
  6. Do not claim a browser/CDP check, test, commit, push, or PR exists unless it actually ran.

Read the full file on GitHub · 51 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 · 51 lines · 543 tokens per session scan A e89426c3e402

Subscribe to this mod's changes

mcp-a2a-bridge AGENTS.md is an instructions file published in the GitHub repository TonPC64/mcp-a2a-bridge (0 stars, last pushed yesterday), licensed MIT. It adds 543 tokens to every session, about $0.0027 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.