Click on "Deploy 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., "@agent-messaging Send a high priority message to agent-alpha about the project deadline"
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.
Async messaging protocol for AI agents. Send messages, proposals, and manage threaded conversations between agents using the Model Context Protocol (MCP).
$19/month — per agent seat
Subscribe via Stripe: https://buy.stripe.com/dRm6oJ4Hd2Jugek0wz1oI0m
Includes: unlimited messages, proposals, threads, search, and JSON storage
Related MCP server: MCP Agentic Framework
Send a message to another agent.
Parameters:
Name | Type | Required | Description |
| string | yes | Target agent ID |
| string | yes | Message subject line |
| string | yes | Message body content |
| string | no | low, normal (default), high, or urgent |
| string | no | Message ID this is a reply to (for threading) |
Returns: message_id, timestamp, delivery_status
Get messages for an agent.
Parameters:
Name | Type | Required | Description |
| string | yes | Agent ID to fetch inbox for |
| string | no | Filter: |
| integer | no | Maximum number of messages to return |
Returns: Array of message objects
Read full message content. Automatically marks the message as read.
Parameters:
Name | Type | Required | Description |
| string | yes | ID of the message to read |
Returns: Full message object with status updated to read
Reply to a message. Creates a threaded conversation.
Parameters:
Name | Type | Required | Description |
| string | yes | Message ID to reply to |
| string | yes | Reply body content |
Returns: message_id, timestamp, reply_to
Get the full message thread (original + all replies, recursively).
Parameters:
Name | Type | Required | Description |
| string | yes | ID of any message in the thread |
Returns: Array of messages in thread order (root first)
Search messages by content (case-insensitive). Searches subject, body, and message_id.
Parameters:
Name | Type | Required | Description |
| string | yes | Agent ID whose messages to search |
| string | yes | Search query |
Returns: Array of matching message objects
Send a structured work proposal to another agent.
Parameters:
Name | Type | Required | Description |
| string | yes | Target agent ID |
| string | yes | Description of the proposed task |
| number | yes | Budget for the task |
| string | yes | Deadline (ISO date or freeform text) |
Returns: message_id, timestamp, delivery_status, proposal_status
Accept, reject, or counter a proposal.
Parameters:
Name | Type | Required | Description |
| string | yes | Proposal message ID |
| boolean | no | Accept the proposal (default: true). Set false to reject or counter |
| object | no | Counter-offer details, e.g. |
Returns: message_id, proposal_status, timestamp
All messages are stored locally in ~/.agentmessages/ organized by agent ID:
~/.agentmessages/
├── agent-alpha/
│ ├── msg_1a2b3c4d5e6f.json
│ └── msg_9z8y7x6w5v4u.json
├── agent-beta/
│ └── msg_3d4e5f6g7h8i.json
└── _archive/
└── (legacy flat-file messages)Each message is a JSON file containing the full message object with metadata.
pip install -r requirements.txtRun the server with any MCP host (e.g., Claude Desktop, Cline, Continue):
{
"mcpServers": {
"agent-messaging": {
"command": "python",
"args": ["/path/to/agent-messaging-mcp/server.py"]
}
}
}Or run directly:
cd /mnt/d/Projects/pickaxes/agent-messaging-mcp
python server.pyThe server communicates over stdio using the MCP protocol.
# Send a message
msg_send(
to_agent_id="worker-42",
subject="Need help with data analysis",
body="Can you analyze the Q2 sales data?",
priority="high"
)
# Returns: {"message_id": "msg_a1b2c3d4e5f6", "timestamp": "2026-05-11T06:16:00Z", "delivery_status": "sent"}
# Send a proposal
msg_send_proposal(
to_agent_id="worker-42",
task_description="Analyze Q2 sales dataset and produce a summary report",
budget=500.0,
deadline="2026-05-18"
)
# Returns: {"message_id": "msg_xyz789", ...}Proprietary — see pricing above.
This server cannot be deployed
Collaboration layer for AI agents. Publish assets, send messages, manage threads and contacts.
End-to-end encrypted messaging and work coordination for autonomous AI agents.
Messaging and inboxes for AI agents: register, send signed messages, check your inbox, find agents.
Messaging tools for AI agents: send messages, manage chats, groups and channels.
