Enterprise DNAEnterprise DNA

MCP Servers · Communication

AgentTrust — Identity & Trust for A2A Agents

by ai.agenttrust

MCP server for AgentTrust — A2A communication, agent identity, HITL escalation, and prompt injection detection

Visit ai.agenttrust ↗

Our verdict

Not reviewed yet

We have not reviewed AgentTrust — Identity & Trust for A2A Agents yet

No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.

How we review records

From the listing

About AgentTrust — Identity & Trust for A2A Agents

AgentTrust is an MCP server that provides agent identity management, agent-to-agent (A2A) communication, human-in-the-loop (HITL) escalation, and prompt injection detection. It enables developers to enforce trust boundaries and security in multi-agent workflows by standardizing identity and escalation protocols.

Best for

Developers building multi-agent systems that need built-in identity, escalation, or prompt injection defenses

Use cases

  • Securing communication between autonomous agents in a multi-agent system
  • Integrating human oversight into agent decision pipelines via HITL escalation
  • Detecting and mitigating prompt injection attacks in agent interactions

Notes

1 stars on GitHub. Last updated 2026-04-09. Licensed MIT.

Pros

  • Covers critical security needs: agent identity, HITL, and prompt injection detection in one package
  • Leverages the MCP standard for easy integration with compatible agent frameworks
  • Open source with a focused feature set for trust in A2A communication

Cons

  • Very early stage with only 1 star, indicating minimal community adoption and validation
  • Documentation and examples may be limited due to newness
  • Requires understanding of MCP protocol and agent infrastructure to set up

Key facts

What we have checked

Days since the last commit
199
Checked GitHub
GitHub forks
2
Checked GitHub
GitHub stars
1
Checked GitHub
Open issues
0
Checked GitHub
Releases in the last 90 days
0
Checked GitHub

Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.

How to use

How to set it up

As the listing publishes it. We have not run this install.

Install

npx @agenttrust/mcp-server init

Tools exposed

  • agenttrust_email_inbox
  • agenttrust_email_read
  • agenttrust_email_attachment
  • agenttrust_email_send
  • agenttrust_email_reply
  • agenttrust_email_forward
  • agenttrust_email_draft
  • agenttrust_send
  • agenttrust_inbox
  • agenttrust_context
  • agenttrust_reply
  • agenttrust_comment
  • agenttrust_escalate
  • agenttrust_discover
  • agenttrust_drive_upload
  • agenttrust_drive_list
  • agenttrust_drive_download
  • agenttrust_drive_delete
  • agenttrust_drive_usage
  • AGENTTRUST_API_KEY

Clients the listing names (not checked here)

Claude Desktop, Claude Code, Cursor, Windsurf

Example client config

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

Install

Add AgentTrust — Identity & Trust for A2A Agents to your client

Not verified yet

Our lab has not run this server yet. "Config checked" on a client means the recipe matches that client's documented config format; it does not mean we ran it.

Claude Code

Config checked

Run in your terminal (runs on your computer)

claude mcp add --env AGENTTRUST_API_KEY=YOUR_AGENTTRUST_API_KEY --transport stdio agenttrust -- npx -y @agenttrust/mcp-server@1.1.1

Needs AGENTTRUST_API_KEY: replace each YOUR_ value with your own.

Version 1.1.1 · From the Official MCP registry, read · Format checked against Claude Code's config docs

Claude Desktop

Config checked

Add to claude_desktop_config.json (runs on your computer)

{
  "mcpServers": {
    "agenttrust": {
      "command": "npx",
      "args": [
        "-y",
        "@agenttrust/mcp-server@1.1.1"
      ],
      "env": {
        "AGENTTRUST_API_KEY": "YOUR_AGENTTRUST_API_KEY"
      }
    }
  }
}

Needs AGENTTRUST_API_KEY: replace each YOUR_ value with your own.

Version 1.1.1 · From the Official MCP registry, read · Format checked against Claude Desktop's config docs

Cursor

Config checked

Add to .cursor/mcp.json (runs on your computer)

{
  "mcpServers": {
    "agenttrust": {
      "command": "npx",
      "args": [
        "-y",
        "@agenttrust/mcp-server@1.1.1"
      ],
      "env": {
        "AGENTTRUST_API_KEY": "YOUR_AGENTTRUST_API_KEY"
      }
    }
  }
}

Needs AGENTTRUST_API_KEY: replace each YOUR_ value with your own.

Version 1.1.1 · From the Official MCP registry, read · Format checked against Cursor's config docs

VS Code

Config checked

Add to .vscode/mcp.json (runs on your computer)

{
  "inputs": [
    {
      "type": "promptString",
      "id": "agenttrust-api-key",
      "description": "Your AgentTrust API key from https://agenttrust.ai",
      "password": true
    }
  ],
  "servers": {
    "agenttrust": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@agenttrust/mcp-server@1.1.1"
      ],
      "env": {
        "AGENTTRUST_API_KEY": "${input:agenttrust-api-key}"
      }
    }
  }
}

Needs AGENTTRUST_API_KEY: replace each YOUR_ value with your own.

Version 1.1.1 · From the Official MCP registry, read · Format checked against VS Code's config docs

Codex

Config checked

Add to ~/.codex/config.toml (runs on your computer)

[mcp_servers.agenttrust]
command = "npx"
args = ["-y", "@agenttrust/mcp-server@1.1.1"]
env_vars = ["AGENTTRUST_API_KEY"]

Needs AGENTTRUST_API_KEY: replace each YOUR_ value with your own.

Version 1.1.1 · From the Official MCP registry, read · Format checked against Codex's config docs

  • ChatGPT: ChatGPT connects only to remote servers that need no API key.

Recipes come from the server's entry in the official MCP registry. Check the package name before you run it, and keep keys out of shared files.

Works with

What AgentTrust — Identity & Trust for A2A Agents connects to

5 clients, each with how we know and when we checked.

Works withTypeHow we knowChecked
Claude CodeClientInstall recipe matches the client's documented formatRuns locally, version 1.1.1Config checkedClaude Code docs
Claude DesktopClientInstall recipe matches the client's documented formatRuns locally, version 1.1.1Config checkedClaude Desktop docs
CursorClientInstall recipe matches the client's documented formatRuns locally, version 1.1.1Config checkedCursor docs
VS CodeClientInstall recipe matches the client's documented formatRuns locally, version 1.1.1Config checkedVS Code docs
CodexClientInstall recipe matches the client's documented formatRuns locally, version 1.1.1Config checkedCodex docs

Health and security

Is AgentTrust — Identity & Trust for A2A Agents looked after, and what do its setup files show

Health score

44 out of 100

Does someone look after this repository? It does not say the code is good or safe. Worked out from GitHub signals checked . How it is worked out

PartPointsWhat we saw
Recent activity14.9 of 30Last push 199 days ago
Releases0 of 150 releases in 90 days
Issue repliesNot countedThe latest check has no issue response reading (fewer than 3 measured issues, or issues switched off)
Maintainer0 of 15Owned by a single user
Official source20 of 20Official server

Sources

Where this comes from

  • GitHubRegistry

    Checked · Days since the last commit, GitHub forks, GitHub stars, Open issues, Releases in the last 90 days

A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.

Changelog

What changed

No changes recorded yet. Releases, price changes and deprecations appear here, with their dates, once we track them for this record.

Pairs with

Other entries in the index that connect to this one. Click through to see the chain.

Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

← Back to MCP ServersSubmit your own entry →