# Agent Safe Message MCP (verified)

A suite of MCP tools that scan every message, image, and video your AI agent handles.

## Quick Start

```bash
# Connect this server (installs CLI if needed)
npx -y @smithery/cli@latest mcp add agent-safe-email/agentsafeemail

# Browse available tools
npx -y @smithery/cli@latest tool list agent-safe-email/agentsafeemail

# Get full schema for a tool
npx -y @smithery/cli@latest tool get agent-safe-email/agentsafeemail check_email_safety

# Call a tool
npx -y @smithery/cli@latest tool call agent-safe-email/agentsafeemail check_email_safety '{}'
```

## Direct MCP Connection

Endpoint: `https://agentsafeemail--agent-safe-email.run.tools`

## Tools (11)

- `check_email_safety` — Analyze an email for phishing, social engineering, prompt injection, and other threats targeting AI agents. Returns ver…
- `check_url_safety` — Analyze one or more URLs for phishing, malware, redirects, and spoofing. Returns per-URL and overall verdicts. $0.01/ca…
- `check_response_safety` — Check a draft email reply BEFORE sending for data leakage, social engineering compliance, and unauthorized disclosure. …
- `analyze_email_thread` — Analyze a full email conversation thread for escalating social engineering, scope creep, and manipulation patterns. $0.…
- `check_attachment_safety` — Assess email attachments for malware risk based on filename, MIME type, and size BEFORE opening/downloading. $0.01/call…
- `check_sender_reputation` — Verify sender identity and detect Business Email Compromise (BEC), spoofing, and impersonation. Includes live DNS DMARC…
- `check_message_safety` — Analyze non-email messages (SMS, WhatsApp, Instagram DMs, Discord, Slack, Telegram, LinkedIn, Facebook Messenger, iMess…
- `check_media_authenticity` — Analyze an image or short video to assess whether it is AI-generated, deepfaked, or authentic. Uses multi-layer analysi…
- `check_prompt_injection_db` — FREE — Query a database of known prompt injection attacks observed in the wild on agent social networks. Returns recent…
- `assess_message` — FREE triage tool — send whatever context you have (message content, sender info, URLs, attachments, draft replies, thre…
- `submit_feedback` — FREE — Submit feedback about any Agent Safe tool you used. Helps us improve detection accuracy and tool quality. No cha…

```bash
# Get full input/output schema for a tool
npx -y @smithery/cli@latest tool get agent-safe-email/agentsafeemail <tool-name>
```

## Resources

- `agentsafe://catalog` — Agent Safe tool catalog with descriptions, parameters, and pricing for all 8 security tools + 2 free tools

## Prompts (1)

- `security-scan-guide` (messageType) — Guides an AI agent to choose the right Agent Safe security tool for a given message, URL, attachment, or sender. Return…