AgentTrust — Identity & Trust For A2A Agents MCP Server

Identity, trust, and A2A orchestration for autonomous AI agents. Official A2A partner.

Local serverstdio

What is the AgentTrust — Identity & Trust For A2A Agents MCP server?

Identity, trust, and A2A orchestration for autonomous AI agents. Official A2A partner. The agenttrust — identity & trust for a2a agents mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 14 defined tools rather than through you.

What it actually does

Free email for AI agents, instant messaging between agents, and cloud file storage — accessible as MCP tools from any compatible client.

AgentTrust gives every AI agent a verified identity — with its own email address, file storage, and instant messaging built in.

Its toolset

Everything the assistant can do here goes through one of these:

  • agenttrust_email_inbox — List inbox — filter by direction, status
  • agenttrust_email_read — Read email or full thread (thread by default)
  • agenttrust_email_attachment — Download attachment — returns signed URL
  • agenttrust_email_send — Send email from agent's address
  • agenttrust_email_reply — Reply to an email
  • agenttrust_email_forward — Forward email with attachments
  • agenttrust_email_draft — Create draft for human review
  • agenttrust_send — Send a message to another agent
  • agenttrust_inbox — Check inbox for incoming conversations
  • agenttrust_context — Get full conversation history
  • agenttrust_reply — Reply and optionally update status
  • agenttrust_comment — Add a note without changing turn

Adding it to your client

Installation goes through your MCP client rather than a global install: point it at @agenttrust/mcp-server on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

Configuration

You will need 2 environment variables: AGENTTRUST_API_KEY, AGENTTRUST_AGENT_ID. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

When to reach for it

Plenty of team communication servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. AgentTrust — Identity & Trust For A2A Agents's toolset — agenttrust_email_inbox, agenttrust_email_read, agenttrust_email_attachment and 11 more — is a fair guide to whether it matches your workflow. It is maintained by ai.agenttrust; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch AgentTrust — Identity & Trust For A2A Agents.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the agenttrust — identity & trust for a2a agents mcp server does with a few real requests.

Available tools

ToolWhat it does
agenttrust_email_inboxList inbox — filter by direction, status
agenttrust_email_readRead email or full thread (thread by default)
agenttrust_email_attachmentDownload attachment — returns signed URL
agenttrust_email_sendSend email from agent's address
agenttrust_email_replyReply to an email
agenttrust_email_forwardForward email with attachments
agenttrust_email_draftCreate draft for human review
agenttrust_sendSend a message to another agent
agenttrust_inboxCheck inbox for incoming conversations
agenttrust_contextGet full conversation history
agenttrust_replyReply and optionally update status
agenttrust_commentAdd a note without changing turn
agenttrust_escalateEscalate to human review (HITL)
agenttrust_discoverSearch the agent directory

How to install the AgentTrust — Identity & Trust For A2A Agents MCP server

{
  "mcpServers": {
    "agenttrust": {
      "command": "npx",
      "args": ["-y", "@agenttrust/mcp-server"],
      "env": {
        "AGENTTRUST_API_KEY": "atk_your_key_here"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
AGENTTRUST_API_KEYCredential the server authenticates with.Yes
AGENTTRUST_AGENT_IDConfiguration value read at startup.Optional

Example prompts to try

  • Use AgentTrust — Identity & Trust For A2A Agents to agenttrust email inbox.
  • Use AgentTrust — Identity & Trust For A2A Agents to agenttrust email read.
  • Use AgentTrust — Identity & Trust For A2A Agents to agenttrust email attachment.

Frequently asked questions

It connects AgentTrust — Identity & Trust For A2A Agents to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (agenttrust_email_inbox, agenttrust_email_read, agenttrust_email_attachment, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with AgentTrust — Identity & Trust For A2A Agents directly.