Agentsafe

io.github.andyscott88Published by GitHub account andyscott88v1.0.1Updated Oct 25, 2026

Real-time URL trust scoring for AI agents. Blocks phishing and malicious sites.

VerifiedSTDIODesktop onlyWeb Search & ScrapingSecurity & Monitoring

Overview

AI-generated overview

AgentSafe is a local MCP server that gives an AI assistant real-time URL trust scoring, so it can check links and block phishing and malicious sites.

What you can do
Score URLs in real time for trust before an assistant acts on them. Flag and block phishing and malicious sites. The manifest lists no individual tools, so the exact operations are not documented here.
When to use it
Worth adding when an assistant follows links, fetches pages, or handles user-supplied URLs and you want a trust check before it proceeds.
Requirements
Runs as a local process on the user's machine via the npm package agentsafe-mcp-server over stdio. Requires an AgentSafe API key supplied in the AGENTSAFE_API_KEY environment variable, obtained from the provider. Desktop only; network access is implied by real-time scoring.
Before you install
Requires an API key in AGENTSAFE_API_KEY; keep it out of shared logs and configs. URLs the assistant checks are sent to the AgentSafe service for scoring, so link contents and destinations leave the machine. Scoring is advisory and may not catch every malicious site.

Installation

In SourceWeft

  1. Open Agentsafe in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

This repository has no README.

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.1LatestSep 16, 2026

Score

25% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.