Agent Safe

io.github.wowcoolPublished by GitHub account wowcoolv1.0.0Updated Oct 24, 2026

Email safety MCP server. Detects phishing, prompt injection, CEO fraud for AI agents.

VerifiedStreamable HTTPWeb executableCommunication & CollaborationSecurity & Monitoring

Overview

AI-generated overview

A remote email-safety MCP server that lets an assistant check emails for phishing, prompt injection and CEO fraud.

What you can do
Check an email for safety, with detection aimed at phishing, prompt injection and CEO fraud for AI agents. The manifest lists no individual tools, so the exact operations are not documented; the service is described as an email safety checker billed per check.
When to use it
Use it when an assistant processes incoming email and you want an automated safety verdict before acting on a message, for example to flag suspected phishing or impersonation attempts.
Requirements
A remote streamable HTTP endpoint at agentsafe.locationledger.com. A Skyfire PAY token is required in the skyfire-pay-id header; the token is obtained from Skyfire. Each email check is charged $0.02.
Before you install
The skyfire-pay-id header carries a payment credential, and every email check costs $0.02, so usage spends money. Email content submitted for checking is sent to a third-party service. No tool list or README is provided, so the exact data handling is undocumented.

Installation

In SourceWeft

  1. Open Agent Safe in the dashboard and add it to a workspace.
  2. Connect skyfire-pay-id credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.wowcool%2Fagentsafe/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "agent-safe": {
      "type": "http",
      "url": "https://agentsafe.locationledger.com/mcp",
      "headers": {
        "skyfire-pay-id": "<YOUR_API_KEY>"
      }
    }
  }
}

Tools

0
This server asks for a credential such as an API key, so SourceWeft could not read its tools without one and has not indexed them.

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

39% 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 daysRequired25 pts

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

  • Auth declaredRequired10 pts
  • 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.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.