# multi-agent-trust-verifier

The #1 ranked OWASP ASI01 risk is Agent Goal Hijack — when an agent gets manipulated into doing something it was never hired to do. This service is your external policy engine. It compares every prop…

## Quick Start

```bash
# Connect this server (installs CLI if needed)
npx -y @smithery/cli@latest mcp add found402/multi-agent-trust-verifier

# Browse available tools
npx -y @smithery/cli@latest tool list found402/multi-agent-trust-verifier

# Get full schema for a tool
npx -y @smithery/cli@latest tool get found402/multi-agent-trust-verifier verify_agent_trust

# Call a tool
npx -y @smithery/cli@latest tool call found402/multi-agent-trust-verifier verify_agent_trust '{}'
```

## Direct MCP Connection

Endpoint: `https://multi-agent-trust-verifier--found402.run.tools`

## Tools (1)

- `verify_agent_trust` — Verifies trust between agents by checking goal alignment, spend limits, action scope, and detecting goal drift. Returns…

```bash
# Get full input/output schema for a tool
npx -y @smithery/cli@latest tool get found402/multi-agent-trust-verifier <tool-name>
```