Agent Safe Message MCP

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

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Check Email Safety: Analyze an email for phishing, social engineering, prompt injection, and other threats targeting AI agents. Returns verdict, risk score, threats, and recommended actions. $0.01/cal
  • Check Url Safety: Analyze one or more URLs for phishing, malware, redirects, and spoofing. Returns per-URL and overall verdicts. $0.01/call via skyfire-api-key header (Skyfire Buyer API Key). By using
  • Check Response Safety: Check a draft email reply BEFORE sending for data leakage, social engineering compliance, and unauthorized disclosure. $0.01/call via skyfire-api-key header (Skyfire Buyer API K

What data it sees

Do you need an account

No: the server works without sign-in

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

Your AI agent processes messages across every platform — but should it trust them? Agent Safe is a 10-tool MCP security suite that protects against phishing, BEC, malware, and manipulation on any messaging platform your agent operates on. Start with the free triage tool to instantly know which checks to run, and use the free feedback tool to help improve detection.

How to connect

How to connect Agent Safe Message MCP to Claude

The server address to paste into Claude settings:

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

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect Agent Safe Message MCP to ChatGPT

The server address to paste into ChatGPT settings:

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

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect Agent Safe Message MCP to Cursor

The server address to paste into Cursor settings:

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

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (11)

Raw names from tools/list. Only developers need these.

check_email_safetyAnalyze an email for phishing, social engineering, prompt injection, and other threats targeting AI agents. Returns verdict, risk score, threats, and recommended actions. $0.01/call via skyfire-api-key header (Skyfire Buyer API Key). By using this service you accept the Terms of Service. Advisory service only.
check_url_safetyAnalyze one or more URLs for phishing, malware, redirects, and spoofing. Returns per-URL and overall verdicts. $0.01/call via skyfire-api-key header (Skyfire Buyer API Key). By using this service you accept the Terms of Service. Advisory service only.
check_response_safetyCheck a draft email reply BEFORE sending for data leakage, social engineering compliance, and unauthorized disclosure. $0.01/call via skyfire-api-key header (Skyfire Buyer API Key). By using this service you accept the Terms of Service. Advisory service only.
analyze_email_threadAnalyze a full email conversation thread for escalating social engineering, scope creep, and manipulation patterns. $0.01/call for <=5 units (4000 tokens each); quote-first for larger threads. Via skyfire-api-key header (Skyfire Buyer API Key). By using this service you accept the Terms of Service. Advisory service only.
check_attachment_safetyAssess email attachments for malware risk based on filename, MIME type, and size BEFORE opening/downloading. $0.01/call via skyfire-api-key header (Skyfire Buyer API Key). By using this service you accept the Terms of Service. Advisory service only.
check_sender_reputationVerify sender identity and detect Business Email Compromise (BEC), spoofing, and impersonation. Includes live DNS DMARC and RDAP domain age checks at no extra cost. $0.01/call via skyfire-api-key header (Skyfire Buyer API Key). By using this service you accept the Terms of Service. Advisory service only.
check_message_safetyAnalyze non-email messages (SMS, WhatsApp, Instagram DMs, Discord, Slack, Telegram, LinkedIn, Facebook Messenger, iMessage, Signal) for platform-specific threats including smishing, wrong-number scams, OTP interception, impersonation, and crypto fraud. $0.01/call via skyfire-api-key header (Skyfire Buyer API Key). By using this service you accept the Terms of Service. Advisory service only.
check_media_authenticityAnalyze an image or short video to assess whether it is AI-generated, deepfaked, or authentic. Uses multi-layer analysis including metadata forensics, error level analysis, ML-based AI detection, and noise pattern analysis. Returns a confidence-scored verdict with per-layer breakdown. $0.04/image (4 units x $0.01), $0.10/video (10 units x $0.01) via skyfire-api-key header. Results are best-guess estimates, not definitive. By using this service you accept the Terms of Service. Advisory service only.
check_prompt_injection_dbFREE — Query a database of known prompt injection attacks observed in the wild on agent social networks. Returns recent injection patterns, payloads, and threat classifications to help agents recognize and avoid manipulation. No charge, no authentication required.
assess_messageFREE triage tool — send whatever context you have (message content, sender info, URLs, attachments, draft replies, thread messages, image/video URLs) and get back a prioritized list of which security tools to run. No AI call, no charge, instant response. Always call this first to get the best security coverage.
submit_feedbackFREE — Submit feedback about any Agent Safe tool you used. Helps us improve detection accuracy and tool quality. No charge, no authentication required.