# Agntor Trust MCP server

Source: https://glimind.com/server/mcp-registry%2Fio.github.agntor%2Ftrust
Registry id: `mcp-registry/io.github.agntor/trust`
Status: unknown

## Install

```json
{
  "mcpServers": {
    "agntor-trust-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@agntor/mcp"
      ]
    }
  }
}
```

Claude Code:

```sh
claude mcp add agntor-trust-mcp-server -- npx -y @agntor/mcp
```

## Tools (14)

- `activate_kill_switch`: Emergency disable an agent
- `check_agent_pulse`: Get real-time health and behavioral metrics
- `create_escrow`: Create a new escrow task for agent-to-agent payment
- `get_agent_card`: Retrieve the verifiable AgentCard (Passport) for an agent
- `get_agent_registration`: Get EIP-8004 compatible registration file for agent discovery
- `get_trust_score`: Calculate comprehensive trust score with behavioral factors
- `guard_input`: Scan incoming prompts for prompt injection and unsafe instructions
- `guard_tool`: Authorize or block tool execution with allow/deny policies
- `is_agent_certified`: Quick boolean check if an agent has valid certification
- `issue_audit_ticket`: Generate signed JWT ticket for x402 transactions
- `query_agents`: Search for agents by trust score, tier, capabilities
- `redact_output`: Redact PII, secrets, and sensitive content from outputs
- `register_agent`: Register a new AI agent in the Agntor trust network
- `verify_agent_identity`: Trigger verification (red-team probes) via the SDK

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.