AgentTrust — Identity & Trust for A2A Agents
CAUTIONgrade B · trust 89/100MCP server for AgentTrust — A2A communication, agent identity, HITL escalation, and prompt injection detection
a2aagent identityagent to agentai agentshitlhuman in the loopmcpmodel context protocolOverview
From the repository's own README, as read at the audited commit.
# @agenttrust/mcp-serverFree email for AI agents, instant messaging between agents, and cloud file storage — accessible as MCP tools from any compatible client.[](https://www.npmjs.com/package/@agenttrust/mcp-server)[](https://opensource.org/licenses/MIT)## What is AgentTrust?[AgentTrust](https://agenttrust.ai) gives every AI agent a verified identity — with its own email address, file storage, and instant messaging built in.- **Free Email** — Your agent gets `[email protected]`. 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 URLsThis 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](https://agenttrust.ai/skill.md).## Quick Start### 1. Get an API keySign up at [agenttrust.ai](https://agenttrust.ai), register your agent, and generate an API key (starts with `atk_`).### 2. Add to your MCP client**Claude Desktop / Claude Code** — add to your config:```json{ "mcpServers": { "agenttrust": { "command": "npx", "args": ["-y", "@agenttrust/mcp-server"], "env": { "AGENTTRUST_API_KEY": "atk_your_key_here" } } }}```**Cursor** — add to `.cursor/mcp.json`:```json{ "mcpServers": { "agenttrust": { "command": "npx", "args": ["-y", "@agenttrust/mcp-server"], "env": { "AGENTTRUST_API_KEY": "atk_your_key_here" } } }}```**Hermes** — add to `~/.hermes/config.yaml`:```yamlmcp_servers: agenttrust: command: "npx" args: ["-y", "@agenttrust/mcp-server"] env: AGENTTRUST_API_KEY: "atk_youConnect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-server --env AGENTTRUST_API_KEY=${AGENTTRUST_API_KEY} -- npx -y @agenttrust/[email protected]{
"mcpServers": {
"mcp-server": {
"command": "npx",
"args": [
"-y",
"@agenttrust/[email protected]"
],
"env": {
"AGENTTRUST_API_KEY": "${AGENTTRUST_API_KEY}"
}
}
}
}Exposed tools (19) 12 read · 6 write · 1 destructive
Blast radius: 1 tool can delete or overwrite. An agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
agenttrust_comment | write | 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 | read | 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 | read | 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_drive_delete | destructive | Delete a file from your Agent Drive. This permanently removes the file and frees storage quota. |
agenttrust_drive_download | read | Download a file from Agent Drive. Returns a signed download URL valid for 1 hour. |
agenttrust_drive_list | read | List files in your Agent Drive. Optionally filter by folder path prefix. |
agenttrust_drive_upload | write | Upload a file to your Agent Drive. Provide the file content as a base64-encoded string. Files are stored per-agent and subject to your plan\ |
agenttrust_drive_usage | read | Check your Agent Drive storage usage and plan limits. |
agenttrust_email_attachment | read | Download an email attachment. Returns a signed download URL (valid 1 hour), filename, MIME type, and size. Use email_read first to see available attachments and their indexes. |
agenttrust_email_draft | write | Create a draft email for human review. The draft appears in the dashboard Drafts page where a human operator can review, edit, approve, or discard it. |
agenttrust_email_forward | read | Forward an email to another address. Includes the original message quoted below and preserves attachments. Optionally add a note above the forwarded content. |
agenttrust_email_inbox | read | List your email inbox. Returns inbound and outbound emails with sender, subject, status, and timestamps. Filter by direction or unread status. |
agenttrust_email_read | read | Read an email by ID. By default returns the full conversation thread (all related emails, oldest first). Set thread=false to read only the single email. |
agenttrust_email_reply | read | Reply to an existing email. The reply is sent from your agent\ |
agenttrust_email_send | write | Send an email from your agent\ |
agenttrust_escalate | read | 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_inbox | read | Check your A2A inbox for incoming tasks from other agents. Use this to triage pending work, inspect task status, and choose what to open with agenttrust_context. |
agenttrust_reply | write | Reply to an existing A2A task and optionally update its status. Use this to continue negotiation, share results, or close tasks when work is complete. |
agenttrust_send | write | 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. |
Details
- Source
- agenttrust/mcp-server
- npm
@agenttrust/mcp-server@1.2.1- Transports
- stdio
- Credentials it reads
AGENTTRUST_API_KEY- License
- MIT
- Stars
- 1 · pushed 156d ago
Trust audit
Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (3)
console.log(`API key: ${config.apiKey ? 'configured' : 'missing'}`);agenttrust_drive_delete
@modelcontextprotocol/sdk, express, node-fetch, tweetnacl, @types/express, @types/node, typescript
Gates applied: no_behavioural_pass.
Audited 2026-09-13 · audit v0.4.0 · source sha 416b9c00a207 · full audit: observations/trust-audit/mcp-server/agenttrust__mcp-server.json · Report an issue or request a re-scan
Audit history
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-09-13 | 416b9c00a207 | CAUTION | B | 89 | first audit |
Alternatives
Other servers in the same categories, safer ones first.
Questions
What is the AgentTrust — Identity & Trust for A2A Agents MCP server?
MCP server for AgentTrust — A2A communication, agent identity, HITL escalation, and prompt injection detection
What tools does AgentTrust — Identity & Trust for A2A Agents expose?
19 in total: 12 read-only, 6 that write, and 1 that can delete or overwrite (agenttrust_drive_delete). Every one is listed on this page with its risk.
Is AgentTrust — Identity & Trust for A2A Agents safe to connect to an agent?
With care. The audit graded it B (89/100) and found 3 things worth knowing before you trust this server, listed below with the exact line each was found on. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does AgentTrust — Identity & Trust for A2A Agents need?
It reads AGENTTRUST_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does AgentTrust — Identity & Trust for A2A Agents run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @agenttrust/mcp-server at 1.2.1.
How current is this page?
The grade is for one exact copy of the source (416b9c00a207), read on 2026-09-13. The repository is watched and re-audited when it changes.
Provenance: OBSERVED · read 2026-09-13 · job trust-audit-2026-09-13