// MCP TOOL REFERENCE

AGENT SAFE TOOLS

11 tools from the Agent Safe MCP Server, categorised by risk level.

View the Agent Safe policy → Token cost: 2,990 tokens →

// ALL 11 AGENT SAFE TOOLS

READ 9 tools

Read analyze_email_thread Analyze a full email conversation thread for escalating social engineering, scope creep, and manipulation p... Read check_attachment_safety Assess email attachments for malware risk based on filename, MIME type, and size BEFORE opening/downloading... Read check_email_safety Analyze an email for phishing, social engineering, prompt injection, and other threats targeting AI agents.... Read check_media_authenticity Analyze an image or short video to assess whether it is AI-generated, deepfaked, or authentic. Uses multi-l... Read check_message_safety Analyze non-email messages (SMS, WhatsApp, Instagram DMs, Discord, Slack, Telegram, LinkedIn, Facebook Mess... Read check_prompt_injection_db FREE — Query a database of known prompt injection attacks observed in the wild on agent social networks. Re... Read check_response_safety Check a draft email reply BEFORE sending for data leakage, social engineering compliance, and unauthorized ... Read check_sender_reputation Verify sender identity and detect Business Email Compromise (BEC), spoofing, and impersonation. Includes li... Read check_url_safety Analyze one or more URLs for phishing, malware, redirects, and spoofing. Returns per-URL and overall verdic...

WRITE 1 tools

Write submit_feedback FREE — Submit feedback about any Agent Safe tool you used. Helps us improve detection accuracy and tool qua...

EXECUTE 1 tools

Execute assess_message FREE triage tool — send whatever context you have (message content, sender info, URLs, attachments, draft r...

// FAQ

How many tools does the Agent Safe MCP server have? +

The Agent Safe MCP server exposes 11 tools across 3 categories: Read, Write, Execute.

How do I enforce policies on Agent Safe tools? +

Route the Agent Safe server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Agent Safe tools fall into? +

Agent Safe tools are categorised as Read (9), Write (1), Execute (1). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.