← Registry

Security & Testing

agentprobe.io

Run security scans on URLs and retrieve reports.

1 endpoint3 known toolsFirst detected July 5, 2026Last detected July 5, 2026

ENDPOINT 1

https://agentprobe.io/mcp

No auth detected

Known tools 3

scan_url

Run a new AgentProbe scan against a URL.

Inferred read-only
get_report

Fetch a previously generated AgentProbe report by ID.

Inferred read-only
list_recent_reports

List recently generated AgentProbe reports.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.agentprobe-io]
url = "https://agentprobe.io/mcp"
enabled = true
Claude Code

.mcp.json

{
  "mcpServers": {
    "agentprobe-io": {
      "type": "http",
      "url": "https://agentprobe.io/mcp"
    }
  }
}
Claude Desktop

Settings → Connectors → Add custom connector

Name: agentprobe-io
Remote MCP URL: https://agentprobe.io/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "agentprobe-io": {
      "url": "https://agentprobe.io/mcp"
    }
  }
}
Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code
{
  "servers": {
    "agentprobe-io": {
      "type": "http",
      "url": "https://agentprobe.io/mcp"
    }
  }
}
Generic MCP

Client-specific MCP configuration

{
  "name": "agentprobe-io",
  "transport": "streamable-http",
  "url": "https://agentprobe.io/mcp"
}
MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for agentprobe.io was fetched 2026-07-25T21:29:46.583Z and is being refreshed.

Trust status Neutral

agentprobe.io is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.