A2A MCP Server
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@A2A MCP Serverlist available agents"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A2A MCP Server
An MCP server that implements an A2A Client for the A2A Protocol. The server can be used to connect and send messages to A2A Servers (remote agents).
The server needs to be initialised with one or more Agent Card URLs, each of which can have custom headers for authentication, configuration, etc.
All agents (name and description) can be viewed with the get_agents tool, an agent's skills (name and description) can be viewed with the get_agent tool, Messages can be sent to the agents with the send_message tool, long-running Tasks can be polled with get_task, and Artifacts can be viewed with view_text_artifact and view_data_artifact tools.
✨ Features
6 MCP tools —
get_agents,get_agent,send_message,get_task,view_text_artifact, andview_data_artifactfor communicating with A2A agentsSimple message sending — send messages to any A2A agent by ID; Agent Card fetching, headers, and non-blocking streaming are handled automatically
Multi-turn conversations — continue conversations across multiple messages using
context_idLong-running task support — if
send_messagetimes out, useget_taskto monitor the task until it reaches a terminal stateAutomatic artifact minimization — large text and data artifacts are automatically minimized for LLM context windows, with dedicated tools for detailed navigation
Task and file storage — tasks and file artifacts are saved locally to
~/.a2a-mcp/by defaultCustom headers and authentication — configure per-agent custom headers for API keys and other credentials
Configurable timeouts and limits — customisable timeouts, polling intervals, and character limits via environment variables
📋 Requirements
To run the server you need to install uv if you haven't already.
MacOS/Linux:
curl -LsSf https://astral.sh/uv/install.sh | shWindows:
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"🚀 Quick Start
Download Claude for Desktop
Add the below to your Claude Desktop config (
~/Library/Application Support/Claude/claude_desktop_config.jsonon macOS):
{
"mcpServers": {
"a2a": {
"command": "uvx",
"args": ["a2anet-mcp"],
"env": {
"A2A_MCP_AGENT_CARDS": "{\"tweet-search\": {\"url\": \"https://example.com/.well-known/agent-card.json\"}}"
}
}
}
}Tip: If you don't have an Agent Card URL, see: A2A Net Demo
⚙️ Configuration
All configuration is via environment variables prefixed with A2A_MCP_.
A2A_MCP_AGENT_CARDS (required)
A JSON object mapping agent IDs to their configuration. Each agent must have a url key with the full path to the Agent Card. It can optionally have a custom_headers key with an object in the form {"header": "value"}:
export A2A_MCP_AGENT_CARDS='{
"tweet-search": {
"url": "https://example.com/.well-known/agent-card.json",
"custom_headers": {"X-API-Key": "your-key"}
}
}'Optional settings
Env Var | Default | Description |
|
| Enable task persistence via |
|
| Enable file artifact storage via |
|
| Character limit for artifact minimization in |
|
| Max string length when minimizing objects |
|
| Character limit for |
|
| Timeout in seconds for fetching agent cards |
|
| Timeout in seconds for |
|
| Timeout in seconds for |
|
| Interval in seconds between |
🛠️ Tools
get_agents
Get all agent names and descriptions.
get_agent
Get an agent's name, description, and skill names and descriptions.
Parameter | Required | Description |
| Yes | Agent ID |
send_message
Send a message to an agent.
Parameter | Required | Description |
| Yes | Agent ID from |
| Yes | Your message or request |
| No | Continue an existing conversation |
| No | Task ID for input_required flows |
| No | Override HTTP timeout (seconds) |
get_task
Get the current state of a task. Monitors until terminal/actionable state or timeout. On timeout, returns the current task state (which may still be non-terminal).
Parameter | Required | Description |
| Yes | Agent ID that owns the task |
| Yes | Task ID from a previous |
| No | Override monitoring timeout (seconds) |
| No | Override interval between polls (seconds) |
view_text_artifact
View text content from an artifact with optional line or character range selection.
Parameter | Required | Description |
| Yes | Agent ID that produced the artifact |
| Yes | Task ID containing the artifact |
| Yes | Artifact to view |
| No | Starting line number (1-based, inclusive) |
| No | Ending line number (1-based, inclusive) |
| No | Starting character index (0-based) |
| No | Ending character index (0-based) |
view_data_artifact
View structured data from an artifact with optional filtering.
Parameter | Required | Description |
| Yes | Agent ID that produced the artifact |
| Yes | Task ID containing the artifact |
| Yes | Artifact to view |
| No | Dot-separated path to extract specific fields |
| No | Row selection (index, list, range string, or "all") |
| No | Column selection (name, list, or "all") |
📖 Examples
List agents
get_agents({}){
"tweet-search": {
"name": "Tweet Search",
"description": "Find and analyze tweets by keyword, URL, author, list, or thread. Filter by language, media type, engagement, date range, or location. Get a clean table of tweets with authors, links, media, and counts; then refine the table and generate new columns with AI."
}
}Get agent details
get_agent({
"agent_id": "tweet-search"
}){
"name": "Tweet Search",
"description": "Find and analyze tweets by keyword, URL, author, list, or thread. Filter by language, media type, engagement, date range, or location. Get a clean table of tweets with authors, links, media, and counts; then refine the table and generate new columns with AI.",
"skills": [
{
"name": "Search Tweets",
"description": "Search X by keywords, URLs, handles, or conversation IDs. Filter by engagement (retweets/favorites/replies), dates, language, location, media type (images/videos/quotes), user verification status, and author/reply/mention relationships. Sort by Top or Latest. Return 1-10,000 results."
},
...,
{
"name": "Generate Table",
"description": "Generate a new table from any table with AI. Explain what table you want to generate from, what columns you want to keep, and what new columns you want to generate."
}
]
}Send a message
send_message({
"agent_id": "tweet-search",
"message": "Find tweets about AI from today (January 12, 2026)"
}){
"id": "tsk-123",
"context_id": "ctx-123",
"kind": "task",
"status": {
"state": "completed",
"message": {
"context_id": "ctx-123",
"kind": "message",
"parts": [
{
"kind": "text",
"text": "I found 10 tweets about \"AI\" posted on January 12, 2026. The search parameters used were:\n\n- Search Terms: AI\n- Start Date: 2026-01-12\n- End Date: 2026-01-13\n- Maximum Items: 10\n\nWould you like to see more tweets, or do you want a summary or analysis of these results?"
}
]
}
},
"artifacts": [
{
"artifact_id": "art-123",
"description": "Tweets about AI posted on January 12, 2026.",
"name": "AI Tweets from January 12, 2026",
"parts": [
{
"kind": "data",
"data": {
"records": {
"_total_rows": 10,
"_columns": [
{
"count": 1,
"unique_count": 1,
"types": [
{
"name": "int",
"count": 1,
"percentage": 100.0,
"sample_value": 213,
"minimum": 213,
"maximum": 213,
"average": 213
}
],
"name": "quote.author.mediaCount"
},
...,
{
"count": 10,
"unique_count": 1,
"types": [
{
"name": "bool",
"count": 10,
"percentage": 100.0,
"sample_value": false
}
],
"name": "isPinned"
}
]
},
"_tip": "Data was minimized. Call view_data_artifact() to navigate to specific data."
}
}
]
}
]
}Handle a long-running task
If the remote agent takes longer than A2A_MCP_SEND_MESSAGE_TIMEOUT (default: 60 seconds), send_message returns the task in its current state:
send_message({
"agent_id": "tweet-search",
"message": "Find tweets about AI from today (January 12, 2026)"
}){
"id": "tsk-123",
"context_id": "ctx-123",
"kind": "task",
"status": {
"state": "working",
"message": null
},
"artifacts": []
}Use get_task to check progress:
get_task({
"agent_id": "tweet-search",
"task_id": "tsk-123"
})When complete, the response matches the format shown in Send a message. If still working, call get_task again to continue monitoring.
Multi-turn conversation
Use context_id to continue a conversation:
send_message({
"agent_id": "tweet-search",
"message": "Can you summarize each of the 10 tweets in the table in 3-5 words each? Just give me a simple list with the author name and summary.",
"context_id": "ctx-123"
}){
"id": "tsk-456",
"context_id": "ctx-123",
"kind": "task",
"status": {
"state": "completed",
"message": {
"context_id": "ctx-123",
"kind": "message",
"parts": [
{
"kind": "text",
"text": "Here is a simple list of each tweet's author and a 3-5 word summary:\n\n1. alienofeth – Real-time STT intent detection\n2. UnderdogEth_ – AI ownership discussion thread\n3. Count_Down_000 – Learning new vocabulary word\n4. ThaJonseBoy – AI and market predictions\n5. Evelyn852422353 – AI model comparison debate\n6. SyrilTchouta – Language learning with AI\n7. cx. – AI in marketing insights\n8. Halosznn_ – Graphic design course shared\n9. xmaquina – AI smarter models discussion\n10. Flagm8_ – AI and business strategy\n\nLet me know if you want more details or a different format!"
}
]
}
},
"artifacts": [
{
"artifact_id": "art-456",
"description": "A simple list of each tweet's author and a 3-5 word summary of the tweet content.",
"name": "AI Tweet Summaries 3-5 Words",
"parts": [
{
"kind": "data",
"data": {
"records": [
{
"author.userName": "ai_q2_",
"summary": "Possibly understand"
},
...,
{
"author.userName": "CallStackTech",
"summary": "Real-time STT intent detection"
}
]
}
}
]
}
]
}View data artifact
view_data_artifact({
"agent_id": "tweet-search",
"task_id": "tsk-123",
"artifact_id": "art-123",
"json_path": "records",
"rows": "all",
"columns": ["author.userName", "text"]
}){
"artifact_id": "art-123",
"description": "Tweets about AI posted on January 12, 2026.",
"name": "AI Tweets from January 12, 2026",
"parts": [
{
"kind": "data",
"data": [
{
"author.userName": "ai_q2_",
"text": "@nyank_x わかるかもしれない"
},
...,
{
"author.userName": "CallStackTech",
"text": "Just built a real-time STT pipeline that detects intent faster than you can say \"Hello!\" 🎤✨ Discover how I used Deepgram to achieve su...\n\n🔗 https://t.co/dgbvdlATZ0\n\n#VoiceAI #AI #BuildInPublic"
}
]
}
]
}💾 Data Storage
Tasks and file artifacts are persisted locally at ~/.a2a-mcp/:
Tasks:
~/.a2a-mcp/tasks/Files:
~/.a2a-mcp/files/
Both can be disabled via environment variables (A2A_MCP_TASK_STORE=false, A2A_MCP_FILE_STORE=false).
🔧 Development
Claude Desktop Setup
For local development:
Clone the repository:
git clone https://github.com/a2anet/a2a-mcp.gitDownload Claude for Desktop.
Add to the below to your Claude Desktop config (
~/Library/Application Support/Claude/claude_desktop_config.jsonon macOS):
{
"mcpServers": {
"a2a": {
"command": "uv",
"args": ["--directory", "/path/to/a2a-mcp", "run", "a2anet-mcp"],
"env": {
"A2A_MCP_AGENT_CARDS": "{\"tweet-search\": {\"url\": \"https://example.com/.well-known/agent-card.json\"}}"
}
}
}
}📄 License
a2anet is distributed under the terms of the Apache-2.0 license.
🤝 Join the A2A Net Community
A2A Net is a site to find and share AI agents and open-source community. Join to share your A2A agents, ask questions, stay up-to-date with the latest A2A news, be the first to hear about open-source releases, tutorials, and more!
🌍 Site: A2A Net
🤖 Discord: Join the Discord
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/a2anet/a2a-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server