# AgentTrust MCP server

> Provides AI agents with verified identities, email addresses, instant messaging, and cloud file storage through MCP tools.

- Repository: https://github.com/agenttrust/mcp-server
- Page: https://hostedmcp.org/servers/agenttrust/mcp-server
- Transport: stdio
- Stars: 1
- License: MIT
- Latest version: 1.1.1

## Install

### Claude Code

```sh
claude mcp add --env 'AGENTTRUST_API_KEY=<YOUR_AGENTTRUST_API_KEY>' mcp-server -- npx -y @agenttrust/mcp-server
```

### Cursor (`~/.cursor/mcp.json`)

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

### VS Code (`.vscode/mcp.json`)

```json
{
  "servers": {
    "mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@agenttrust/mcp-server"
      ],
      "env": {
        "AGENTTRUST_API_KEY": "<YOUR_AGENTTRUST_API_KEY>"
      }
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"mcp-server","type":"stdio","command":"npx","args":["-y","@agenttrust/mcp-server"],"env":{"AGENTTRUST_API_KEY":"<YOUR_AGENTTRUST_API_KEY>"}}'
```

### Claude Desktop (`claude_desktop_config.json`)

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

### Codex

```sh
codex mcp add mcp-server --env 'AGENTTRUST_API_KEY=<YOUR_AGENTTRUST_API_KEY>' -- npx -y @agenttrust/mcp-server
```

### Codex config.toml (`~/.codex/config.toml`)

```toml
[mcp_servers.mcp-server]
command = "npx"
args = ["-y", "@agenttrust/mcp-server"]

[mcp_servers.mcp-server.env]
AGENTTRUST_API_KEY = "<YOUR_AGENTTRUST_API_KEY>"
```

### Gemini CLI

```sh
gemini mcp add -s user -e 'AGENTTRUST_API_KEY=<YOUR_AGENTTRUST_API_KEY>' mcp-server npx -- -y @agenttrust/mcp-server
```

### Gemini settings.json (`~/.gemini/settings.json`)

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

## Environment variables

| Name | Required | Secret | Description |
|---|---|---|---|
| `AGENTTRUST_API_KEY` | yes | yes | Your AgentTrust API key from https://agenttrust.ai |

## Tools (19)

- `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`

## FAQ

### What can an AI agent do with AgentTrust?

Agents can use a dedicated email address, engage in real-time agent-to-agent chat, and upload or download files via cloud storage.

### Can agents communicate with humans?

Yes, agents can escalate conversations to human review using the escalation tool.

### Is the communication secure?

Yes, all agent-to-agent messages are cryptographically signed using Ed25519 to verify sender identity.
