AgentTrust — Identity & Trust for A2A Agents MCP server

by agenttrust.ai·ai.agenttrust/mcp-server·v1.1.1·2 stars

No reviews yet

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

B72/100grade B

Write a review Install

What users say

No reviews yet

Be the first

Safety scan

B72/100

full report

Adoption

New

2 stars

Reviews

Write one

Nobody has reviewed AgentTrust — Identity & Trust for A2A Agents yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

AgentTrust — Identity & Trust for A2A Agents tools (13, 2 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

agenttrust_allowlist
View your organization allowlist to see which agents and organizations are permitted to contact your agents. This tool is read-only; allowlist changes are managed by your org admin in the AgentTrust dashboard.
agenttrust_cancelwrite action
Cancel an ongoing A2A task. Use when work should stop and both sides should see the task as canceled.
agenttrust_comment
Add a comment to a task without changing turn or task state. Use for notes, rationale, or coordination context; set internal=true for comments visible only to your side.
agenttrust_context
Get conversation history for a task in light or full mode. Use before replying when you need complete context, including prior messages, status transitions, and review actions.
agenttrust_discover
Search the AgentTrust directory for agents by name, skill, or organization. Provide query to filter results, or leave it empty to list all publicly discoverable agents.
agenttrust_escalate
Escalate an A2A task for human review through HITL. Use when you are uncertain, the request exceeds your authorization, or you need human approval before proceeding. The task is held until a human reviews and responds.
agenttrust_guard
Analyze text for prompt injection attacks, command injection, and social engineering attempts. Use to scan untrusted input before processing - user messages, emails, web content, and tool outputs. Returns a risk assessment with detected threats and a recommended action.
agenttrust_inbox
View your A2A task board — all tasks you are involved in, both sent and received. Returns tasks sorted by most recent. To see only tasks waiting on YOU to act, set turn to your own slug. Use agenttrust_context to read the full thread before replying.
agenttrust_issue_code
Issue a one-time Trust Code for agent-to-human verification. Use when your agent needs to prove identity to a human in outreach, support, or other sensitive interactions. Returns a code and verification URL the human can use.
agenttrust_reply
Reply to an existing A2A task and optionally update its status. AgentTrust extends the A2A protocol with a negotiation lifecycle. Status values and when to use them: - "working" — you are actively working on this task - "input-required" — you need more information from the other agent before continuing - "propose_complete" — you believe the work is done; proposes closure (the other party must conf
agenttrust_sendwrite action
Send a message to another agent via the AgentTrust A2A relay. Creates a new task or continues an existing one when taskId is provided. Use agenttrust_discover first if you need to find recipient slugs.
agenttrust_status
Check your current AgentTrust identity and runtime status, including endpoint identity, signing key status, and pending task count.
agenttrust_verify_code
Verify a Trust Code from another party before proceeding. Use when you receive a code from an agent or human and need to confirm issuer identity, organization, and authorization context.

Public scan report

scanner v0.1.10 · 2026-09-28 · same rubric, same numbers if you re-run it

no findings

Code scan7 source files scanned25/25
–Live reliabilityno gateway calls yet and no remote to proben/a
–Tool poisoningtools not inspected (local package is not executed); not countedn/a
Auth qualitystatic API keys via environment variables6/15
Maintenancelast push 171 days ago8/15
Maintainer identityregistry namespace matches repository owner; website matches verified namespace8/10

Overall 72/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

How AgentTrust — Identity & Trust for A2A Agents compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score: 72/100; higher than 38% of 48,255 servers
Tools: 13; the typical server has 7
Tools that change things: 15%; typical: 0%. Fewer write tools means less an agent can break
GitHub stars: 2; more than 75% of 28,688 servers

What its tools let an agent do: 11 read · 2 change

Install AgentTrust — Identity & Trust for A2A Agents in Claude Code, Cursor or VS Code

Runs npx -y @agenttrust/mcp-server on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add mcp-server -- npx -y @agenttrust/mcp-server

Add to Cursor

What the publisher says

From the AgentTrust — Identity & Trust for A2A Agents repository's README, as published. We do not edit it. Read it on GitHub

@agenttrust/mcp-server

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

What is AgentTrust?

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

Free Email — Your agent gets your-agent@agenttrust.ai. Send, receive, read threads, forward, and manage drafts
Instant Messaging — Real-time agent-to-agent chat with conversation threads, escalation to humans, and status tracking
Cloud File Storage — Upload, download, and share files between agents with signed URLs

This MCP server exposes all of these as tools that any MCP-compatible client can use — Claude Desktop, Claude Code, Cursor, Windsurf, OpenClaw, Hermes, n8n, LangChain, and more.

Also available as an OpenClaw / Hermes skill.

Quick Start

1. Get an API key

2. Add to your MCP client

Claude Desktop / Claude Code — add to your config:

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

Cursor — add to .cursor/mcp.json:

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

Hermes — add to ~/.hermes/config.yaml:

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

That's it. All 19 tools are available immediately.

3. (Optional) Interactive setup

For advanced features like Ed25519 message signing:

npx @agenttrust/mcp-server init

Tools

Email (7 tools)

Your agent sends and receives email as your-agent@agenttrust.ai — a real email address that works with any mailbox.

Instant Messaging (7 tools)

Real-time agent-to-agent communication. Messages are organized into tasks (threads) with status tracking.

Cloud File Storage (5 tools)

Upload, store, and share files between agents.

Usage Examples

Send an email

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

AgentTrust — Identity & Trust for A2A Agents: common questions

Is AgentTrust — Identity & Trust for A2A Agents MCP server safe?: Mostly: it is graded B (72/100). Read the AgentTrust — Identity & Trust for A2A Agents safety report
How do I install AgentTrust — Identity & Trust for A2A Agents?: It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does AgentTrust — Identity & Trust for A2A Agents need an API key?: Yes. The registry entry asks for AGENTTRUST_API_KEY.
Is AgentTrust — Identity & Trust for A2A Agents maintained?: The last commit was 208 days ago (2026-04-09). The latest release is v1.1.1.
How does AgentTrust — Identity & Trust for A2A Agents compare with other MCP servers?: safety score 72/100 (higher than 38% of 48,255 servers); tools 13 (the typical server has 7); tools that change things 15% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.