What is a2a-mcp-consumption?

Instructions for connecting an MCP client to a limited A2A Mesh bridge and using its reviewed tools. A2A is a protocol for communication between AI agents, while MCP connects clients to tools and services.

Setting up stdio or local HTTP connections, discovering approved A2A agents, sending messages, and checking task status under the documented access policy.

It keeps the connection restricted to approved tools, credentials, agents, and destinations instead of exposing unrestricted access.

a2a-mcp-consumption — Skill for Claude Code and OpenCode by oaslananka

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.

Any agent

npx skills add oaslananka/a2amesh --skill a2a-mcp-consumption

Clone the repo

git clone --depth 1 https://github.com/oaslananka/a2amesh

Made for: Claude Code, OpenCode.

Or install a2amesh, the plugin that ships this one along with the rest of its 3 skills, 1 MCP server.

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/skills/oaslananka/a2amesh/a2a-mcp-consumption/github.svg)](https://agentmods.dev/skills/oaslananka/a2amesh/a2a-mcp-consumption)

Your own site

<a href="https://agentmods.dev/skills/oaslananka/a2amesh/a2a-mcp-consumption"><img src="https://agentmods.dev/badge/skills/oaslananka/a2amesh/a2a-mcp-consumption/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/skills/oaslananka/a2amesh/a2a-mcp-consumption"><img src="https://agentmods.dev/badge/skills/oaslananka/a2amesh/a2a-mcp-consumption.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 740 The whole file, excluding the scripts and references it only reads on demand.

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	$0.00030	$0.00740
Opus 5	$0.00015	$0.00370
Sonnet 5	$0.00006	$0.00148
Haiku 4.5	$0.00003	$0.00074

Measured 10d ago against content hash c41eff239c5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

a2a-mcp-consumption 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 10d 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.

.opencode/skills/a2a-mcp-consumption/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

A2A MCP Consumption

Use this skill to connect an MCP-capable client to the published a2amesh-mcp server and invoke only its reviewed A2A tool surface.

When to use

Use this skill when the user asks to:

connect a local MCP client to A2A Mesh through stdio or loopback Streamable HTTP;
discover the bounded MCP tool set;
diagnose MCP connection or tool-registration failures; or
invoke a2a_discover, a2a_send_message, or a2a_get_task under the documented policy.

This is not an OpenClaw-specific plugin and does not make any client part of the A2A protocol implementation.

Required context

Confirm:

the exact released @a2amesh/mcp version or reviewed local build;
the transport: stdio or loopback Streamable HTTP;
the exact tool allowlist and whether it remains read-only;
expected tenant, audience, scopes, and approval identifiers;
named credential variables already provided by the runtime secret source;
statically allowlisted A2A agents and destinations; and
the requested read-only or state-changing tool invocation.

Workflow

Start from .mcp.json or the matching Codex, VS Code, or OpenCode example.
Prefer stdio for a local one-user flow. Use Streamable HTTP only on loopback with the documented bearer credential.
Keep the default allowlist at a2a_discover,a2a_get_task until a send is explicitly approved.
Run the client's status, doctor, or probe command before any tool call.
Start with a2a_discover for the expected tenant.
Use a2a_get_task only for a known allowlisted agent and task.
Before a2a_send_message, obtain explicit approval, add the send scope and tool, set a fresh scoped approval identifier, and restart the MCP process.
Preserve audit evidence and report bounded reason codes without exposing input or output secrets.

Safety boundaries

Fail closed on tool, tenant, audience, scope, approval, agent, and destination mismatch.
Keep SSRF and outbound-network restrictions enabled.
Never expose terminal, credential, merge, publish, deployment, or destructive tools through this bridge.
Do not place concrete credentials in plugin files, client configuration committed to Git, logs, audit payloads, or chat output.
Treat MCP annotations as hints; server authorization and audit policy remain authoritative.
Bound timeout, cancellation, response size, and task artifact output.
Do not claim generic MCP or A2A conformance from one client probe.

Read the full file on GitHub · 79 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.

10d ago First seen · 79 lines · 30 tokens per session scan A c41eff239c5a

Subscribe to this mod's changes

a2a-mcp-consumption is a skill published in the GitHub repository oaslananka/a2amesh (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 30 tokens to every session and 740 once invoked, about $0.0002 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.

Backend and APIs Building agents a2a a2a-protocol agent-to-agent agents ai-agents cli

frankfurter

Fetch currency exchange rates from the frankfurter.dev API.

a2aproject/a2a-samples · 14 tokens

draw-image

Generate an image from a text prompt using an OpenAI-compatible image generation API (gpt-image-1-mini or compatible). The image is uploaded to the gofile.io public file sharing service and ONLY the public download page URL is returned. Trigger when user asks to draw, paint, generate, or create an image.

ai-sns/ai-sns · 67 tokens

lucid-agents

Build, modify, review, debug, or deploy TypeScript services made with the Lucid Agents SDK. Use whenever a project imports @lucid-agents packages or the user asks about Lucid runtimes, entrypoints, adapters, payments, MPP, identity, wallets, A2A tasks, service UI, scaffolding, or deployment.

daydreamsai/lucid-agents · 75 tokens

a2a-mcp-consumption