A2A to MCP bridge

Name: A2A to MCP bridge
Author: AmirK-S

by AmirK-Sversion 0.1.0i★ 2iRuns on your computer

Registry nameio.github.AmirK-S/a2a-to-mcp

Install

Overview

Description from the maker (original English)

A2A v1.0.1 agents as MCP 2026-07-28 tools, with the tasks extension

PopNx MCP’s three pillars

These three are never merged into one score: opinions, measurements and popularity are different things.

User voiceiNo reviews yetReviews from signed-in users. The average shows once there are reviews
Our basic checksi2 of 2 passedChecked from public information; code not scanned yet
UsageiVery new↓ 34/wk · ★ 2

What you can do with it

We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.

Connection: Runs on your computer
Transport: Streamable HTTP
Category: Other

Install

Pick the AI app you use, then copy the settings.

Before you install

Basic checks: 2 of 2 passed
Runs on your computer with your user’s permissions (files, network, apps).
The registry lists no key to fill in.

You need

npmNode.js installed (for the npx command)

Which app do you use?

ClaudeClaude CodeCursorVS CodeChatGPT

Pick your app above. We remember it, so next time the button says “Install in …”.

Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json

{
  "mcpServers": {
    "a2a-to": {
      "command": "npx",
      "args": [
        "-y",
        "a2a-to-mcp",
        "--config",
        "your-value",
        "--port",
        "8931"
      ]
    }
  }
}

Run this in your terminal

claude mcp add a2a-to -- npx -y a2a-to-mcp --config your-value --port 8931

This one needs values on its command line, so copy the settings and fill them in.

Or copy the settings yourself

Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "a2a-to": {
      "command": "npx",
      "args": [
        "-y",
        "a2a-to-mcp",
        "--config",
        "your-value",
        "--port",
        "8931"
      ]
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

This one needs values on its command line, so copy the settings and fill them in.

Or copy the settings yourself

Paste into .vscode/mcp.json in your project

{
  "servers": {
    "a2a-to": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "a2a-to-mcp",
        "--config",
        "your-value",
        "--port",
        "8931"
      ]
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.

Your choice stays on this device in a cookie; no account needed.

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

Which apps can use it

Based on how this server connects and on each app’s own docs, checked Nov 10, 2026.

Run on your computer in

Claude Goose LM Studio Msty Studio Cherry Studio Cursor VS Code + GitHub Copilot Visual Studio Windsurf (Devin Desktop)Zed Kiro Cline Continue JetBrains AI Assistant Claude Code Codex CLI Gemini CLI OpenCode nodecode Warp LibreChat Raycast

All apps, with pros and cons →

What it can do

Runs on your computer; the tool list appears in your AI app after you install it.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 11, 2026

✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account AmirK-S, which owns the repo
✓ Pass
Still maintained
Code last changed 2 months ago
… Not checked yet
Has a licence
We have not read this repo from GitHub yet
– Not applicable
Endpoint responds
This one runs on your computer; there is no internet endpoint
– Not applicable
Sign-in with OAuth
Runs on your computer and uses local settings instead
… Not checked yet
No hidden instructions in tool descriptions
Runs on your computer; we can only read tool lists from internet endpoints

User reviews

No reviews yet

Compared with others in Otheri

More stars than 91% of the other 19126 servers in this category
Published to the registry more recently than 31% of the other 19126 servers in this category
Basic checks equal to or better than 100% of the other 19126 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is A2A to MCP bridge safe?

It passed 2 of 2 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

The registry does not list a required key, though some servers ask you to sign in on first use.

Does it run on my computer or in the cloud?

It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).

Is it still maintained?

The GitHub repo last changed 2 months ago, and the latest version (0.1.0) reached the registry 2 months ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.

What can I use instead?

In the same category: World Monitor, Claude Flow, Tldraw

Alternatives

Servers in the same category from other makers, sorted by stars.

Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

World Monitor

Real-time global intelligence on conflict, markets, energy, trade, shipping and cyber. 102 tools.

by koala73Widely used★ 90.5KUpdated 6 days ago

Runs in the cloud✓ worldmonitor.app

Install

Claude Flow

AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.

by ruvnetWidely used↓ 13.5K/wk★ 81.4KUpdated 14 months ago

Runs on your computer

Install

Tldraw

Draw and visually collaborate with your agents on tldraw's canvas.

by tldrawWidely used★ 51.4KUpdated 8 months ago

Runs in the cloud

Install

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

a2a-to-mcp

A2A v1.0.1 agents exposed as MCP tools on a stateless MCP 2026-07-28 server, with the io.modelcontextprotocol/tasks extension.

Point the bridge at one or more A2A agents by their agent card. Any MCP client, Claude Code or Cursor among them, then sees four ordinary tools: discover an agent, send it a message, read a task, cancel a task. The bridge translates parts, artifacts, task states and errors between the two protocols and says out loud what it cannot translate.

Surface	Version served	Pinned dependency
MCP, modern route	`2026-07-28` via `server/discover`, no session, per-request `_meta`	`@modelcontextprotocol/server` 2.0.0
MCP, legacy route	`2025-11-25` via `initialize`, same endpoint	same
MCP tasks extension	`io.modelcontextprotocol/tasks` schema `2026-07-28`, modern route only	none, served by the bridge
A2A	`1.0` (`A2A-Version: 1.0`), JSON-RPC binding	`@a2a-js/sdk` 1.1.0

Node 20 or later. Apache-2.0.

Quick start

npm install -g a2a-to-mcp

Or run it from the repository:

git clone https://github.com/AmirK-S/a2a-to-mcp.git && cd a2a-to-mcp && npm ci && npm run build

Write agents.json, one alias per agent, by base URL or by card URL:

"agents": { "hello": { "url": "http://localhost:9999" }, "planner": { "cardUrl": "https://planner.example.org/.well-known/agent-card.json" } }, "port": 8931 }

Run it:

node dist/cli.js --config agents.json

The bridge listens on http://127.0.0.1:8931/mcp. Only loopback hosts are accepted in the Host and Origin headers unless allowedHosts is set in the configuration. There is no authentication in this version, on either side.

Claude Code

Add to .mcp.json at the root of the project, which is the block the bridge prints on startup:

"mcpServers": { "a2a-to-mcp": { "type": "http", "url": "http://127.0.0.1:8931/mcp" } } }

Claude Code negotiates 2026-07-28 through server/discover since its v2 runtime, documented from 2.1.232 and measured here with 2.1.263. Older versions fall back to initialize and get the same four tools on the legacy route. A full annotated trace of a Claude Code session against the bridge, discovery, a task with an artifact and an elicitation round trip, is in docs/DEMO-CLAUDE-CODE.md. In headless mode (claude -p) there is nobody to answer an elicitation, so Claude Code cancels it and the bridge cancels the A2A task; the interactive mode asks the user.

Cursor

Add to .cursor/mcp.json:

"mcpServers": { "a2a": { "url": "http://localhost:8931/mcp" } } }

Cursor speaks 2025-11-25 and is served through initialize on the same endpoint.

The four tools

Every tool takes the agent alias as its first argument when several agents are configured; with a single agent the alias may be omitted and defaults to it.

Tool	Arguments	Returns
`a2a_discover`	`agent`	the agent card as the agent served it, after a structural check, in `structuredContent`, with a text summary and the card URL in `_meta`
`a2a_send_message`	`agent`, `text`, `contextHandle?`, `taskHandle?`	the agent reply, see the result contract below
`a2a_get_task`	`agent`, `taskHandle`, `historyLength?`	the task envelope with its history
`a2a_cancel_task`	`agent`, `taskHandle`	the task envelope after the cancellation request

Calling a tool on the wire

The argument that carries the message is text. A complete tools/call on the 2026-07-28 route, as an MCP client sends it:

curl -sS http://127.0.0.1:8931/mcp \

-H 'Content-Type: application/json' \ -H 'Accept: application/json, text/event-stream' \ -H 'MCP-Protocol-Version: 2026-07-28' \ -H 'Mcp-Method: tools/call' \ -H 'Mcp-Name: a2a_send_message' \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{ "_meta":{"io.modelcontextprotocol/protocolVersion":"2026-07-28", "io.modelcontextprotocol/clientCapabilities":{}}, "name":"a2a_send_message", "arguments":{"agent":"hello","text":"task: hello world"}}}'

A run against a public A2A agent, with the one mistake a first user makes, is in docs/USAGE-REEL.md.

Result contract

Each reply is a CallToolResult whose content holds the translated parts and whose structuredContent is an envelope:

"kind": "task", "contextHandle": "cx_...", "taskHandle": "tk_...", "a2aState": "TASK_STATE_COMPLETED", "status": "completed", "note": "present when the mapping lost information", "artifacts": [{ "artifactId": "...", "name": "result" }], "data": {} }

data holds the single A2A data part of the artifacts, and is absent when there is none or more than one. history is added by a2a_get_task only.

kind is message for a direct A2A message and task when the agent opened a task. Handles are opaque strings minted by the bridge, never A2A identifiers; they hide the bridge table, not what an agent chooses to write in its own messages. They live in memory for fifteen minutes after their last use by default (handleTtlMs), and an expired or unknown handle returns an explicit error. Pass contextHandle back to stay in the same conversation, and taskHandle back to answer a task the agent left waiting for input.

An agent failure (FAILED, REJECTED, AUTH_REQUIRED), and a task the agent left in the unspecified state, is a tool execution error: isError: true, the agent text in content, the A2A state and a note in the envelope. A typed A2A error (codes -32001 to -32009) is also a tool execution error, with the code in structuredContent.a2aErrorCode. The bridge never re-emits an A2A error code as a JSON-RPC code. JSON-RPC reserves -32000 to -32099 for server-defined errors, MCP already uses -32020, -32021 and -32022 in that band, and an A2A code replayed there would claim an MCP meaning it does not have.

Long-running tasks

With the tasks extension

A client that declares io.modelcontextprotocol/tasks in the per-request clientCapabilities.extensions gets a CreateTaskResult from a2a_send_message as soon as the agent opens a task, then polls tasks/get and may call tasks/update and tasks/cancel. The bridge consumes SendStreamingMessage in the background when the card announces streaming, and GetTask otherwise.

A2A `TaskState`	MCP `TaskStatus` on `tasks/get`	What is lost
`SUBMITTED`	`working`	MCP has no accepted but not started state; `statusMessage` says so
`WORKING`	`working`	nothing
`INPUT_REQUIRED`	`input_required` with one synthesized form elicitation	A2A asks in free text; the form has a single string field
`COMPLETED`	`completed`, `result` is the full `CallToolResult`	nothing
`FAILED`, `REJECTED`, `AUTH_REQUIRED`	`completed`, `result.isError` is true	a refusal and an authorization request become indistinguishable from a failure without the envelope
`CANCELED`	`cancelled`	nothing, mind the spelling
unspecified	`completed`, `result.isError` is true	A2A sent no lifecycle at all; the bridge does not guess one
bridge cannot reach the task any more	`failed` with a JSON-RPC `error`, A2A code in `error.data`

AUTH_REQUIRED is deliberately not mapped to input_required: MCP forbids form elicitation for credentials, and A2A asks for out-of-band authorization. The agent text, which usually carries the URL to visit, is returned in the result.

The extension is served on the 2026-07-28 route only. On the legacy route, tasks/* answer -32021 with the required capability. As of 2026-09-06, the two clients measured against this bridge, Claude Code and Cursor, do not declare the extension. It is exercised by the test suite in this repository and by any client that opts in per request.

CreateTaskResult leaves the bridge with an empty content array in addition to the fields the extension defines. That is a workaround for the reference SDK, which validates every tools/call result against the plain result schema (typescript-sdk issue 2637). The three extension methods are served by a small router in front of the SDK on the modern route, because the SDK answers -32601 to tasks/get and tasks/cancel before consulting its handlers (typescript-sdk issue 2598), and splitting the three across two layers would let them drift. Both workarounds are isolated and will be removed when the SDK moves.

Without the extension

a2a_send_message waits for the agent to reach a terminal or interrupted state and answers inline. A task left in INPUT_REQUIRED comes back:

as a multi-round-trip input_required result with one form elicitation, for a client that declares elicitation, which then replays the call with the answer;
as an ordinary result whose envelope says input_required and carries the taskHandle, for any other client, which then sends the answer with that handle.

What crosses the bridge, and what does not

Parts:

A2A `Part`	MCP content block
`text`	`TextContent`
`data`	`TextContent` holding the JSON, flagged in `_meta`; also `structuredContent.data` when it is the only data part of the task artifacts
`url`	`ResourceLink` with `filename` as name and `mediaType` as `mimeType`
`raw`, image or audio media type	`ImageContent` or `AudioContent` in base64
`raw`, other media type	embedded blob resource under an `a2a://part/` URI

filename, artifact identity and name, message and context identifiers travel in _meta["io.github.amirk-s/a2a"] on each block.

Not carried, by design: push notifications (no webhook in MCP), agent card signatures, securitySchemes, streaming events as such (accumulated into the task), ListTasks (handles replace it), and any routing of free text to a skill. The bridge calls no language model and keeps nothing on disk.

Conformance

Read the score with its cause: on the 2026-07-28 run, 32 of the 37 scored scenarios have at least one check that is not green, 29 with a failure and 3 with warnings only. Nineteen call tool names written into the suite, and 13 exercise prompts, resources or completions, which a bridge to A2A agents does not declare; logging is not among them, it is only scored on 2025-11-25. The suite counts both families as failures on purpose, and points at the expected-failures baseline as the answer (modelcontextprotocol/conformance#248). The run records 67 failing checks and 5 warnings in all, every one of them in the committed baseline with its reason; the suite exits 0 on both revisions, and the protocol checks that apply to a bridge are green: wire schema, server/discover, the match between the capabilities announced and the handlers mounted, the subscriptions/listen acknowledgement, SEP-2243 headers, DNS rebinding protection. The numbers are in conformance/REPORT.md, regenerated by the command below.

npm run conformance replays the official suite, @modelcontextprotocol/conformance at 0.2.0-alpha.11, for 2026-07-28 and 2025-11-25, with a baseline of expected failures where every line carries its reason. The report is in conformance/REPORT.md.

What the suite proves: every message the bridge emits validates against the schema of its revision (wire-schema-valid on both wires), server/discover and the stateless wire behave, header validation of SEP-2243 is enforced, DNS rebinding protection is on. What it cannot measure: the scenarios that call the suite's own fixture tools by name, and the tasks-* scenarios, which a bridge to real agents cannot satisfy without pretending to be the fixture. The tasks ext

Only the beginning is shown; read the rest in the repo

A2A to MCP bridge

Overview

PopNx MCP’s three pillars

What you can do with it

Install

Before you install

Which apps can use it

Related guides

What it can do

Basic checksi

Maker matches the repo

Still maintained

Has a licence

Endpoint responds

Sign-in with OAuth

No hidden instructions in tool descriptions

User reviews

Compared with others in Otheri

Common questions

Alternatives

World Monitor

Claude Flow

Tldraw

README from the maker

a2a-to-mcp

Quick start

Claude Code

Cursor

The four tools

Calling a tool on the wire

Result contract

Long-running tasks

With the tasks extension

Without the extension

What crosses the bridge, and what does not

Conformance