Agentsafe
Score URLs in real time inside the agent so phishing and malicious links get blocked before fetch or navigation.
Overview
AgentSafe is a MCP server for the Ship phase that provides real-time URL trust scoring so AI agents can block phishing and malicious sites.
What is this MCP server?
- Real-time URL trust scoring tuned for autonomous AI agents
- Blocks phishing and malicious sites before risky fetches
- stdio npm package agentsafe-mcp-server v1.0.1
- Requires AGENTSAFE_API_KEY from agentsafe.app
- Server version 1.0.1
- npm identifier agentsafe-mcp-server
- One required secret environment variable AGENTSAFE_API_KEY
What problem does it solve?
Agents that browse or fetch user-provided URLs can walk into phishing or malware hosts with no human glance at the bar.
Who is it for?
Solo builders shipping agents that browse the web, read tickets, or resolve arbitrary URLs during development and support.
Skip if: Closed pipelines that never fetch external URLs or teams that already enforce network egress solely at the infra layer with no agent hook.
What do I get? / Deliverables
Link opens and fetches can be checked against AgentSafe trust scores before the agent commits to a dangerous destination.
- MCP tool surface for URL trust checks via agentsafe-mcp-server
- Documented secret handling for AGENTSAFE_API_KEY
- Operational policy for blocking or escalating low-trust URLs in agent prompts
Recommended MCP Servers
Journey fit
How it compares
URL trust MCP guardrail, not a full vulnerability scanner or code review skill.
Common Questions / FAQ
Who is AgentSafe for?
Developers and indie builders who run MCP-enabled agents that need to open or validate URLs and want phishing protection without building their own threat feed.
When should I use AgentSafe?
Use it during Ship security hardening and whenever agents follow links from users, docs, or the open web before production or high-privilege automation.
How do I add AgentSafe to my agent?
Install the npm stdio server agentsafe-mcp-server, set AGENTSAFE_API_KEY from agentsafe.app in your MCP environment, and register the server in Claude Code, Cursor, or your agent’s MCP config.