INDIVIDUAL MCP TOOL

scan_mcp_server

Check an MCP server for real risk signals before trusting it: unauthenticated transport, capability overreach (filesystem/shell/credential access with no scoping), and known-bad signatures.

allthepossibles.comnone authenticationAvailability not checked

LIVE ENDPOINT

https://preflight.allthepossibles.com/mcp

No auth detected

Connect to this endpoint to inspect the live schema for scan_mcp_server and invoke it with your own arguments.

Indexed input schema

{}

Risk classification

Potential side effects detected · medium confidence · heuristic, not a guarantee.

A tool name or description suggests code or command execution.
A tool name, description or schema mentions credentials.

Parent server

allthepossibles.com

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.preflight]
url = "https://preflight.allthepossibles.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "preflight": {
      "type": "http",
      "url": "https://preflight.allthepossibles.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: preflight
Remote MCP URL: https://preflight.allthepossibles.com/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": {
    "preflight": {
      "url": "https://preflight.allthepossibles.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "preflight": {
      "type": "http",
      "url": "https://preflight.allthepossibles.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "preflight",
  "transport": "streamable-http",
  "url": "https://preflight.allthepossibles.com/mcp"
}

MCP Inspector

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

Related tools

scan_content — Check a document or web page for hidden instructions before an agent reads, summarizes, or acts on it: invisible Unicode, obfuscated payloads, and (on Pro) a semantic pass for prompt-injection phrasing aimed at the model instead of the human reader.
scan_extension — Check a VS Code extension or a Claude Skill before installing or trusting it.
check_output — Check a structured output you're about to return or act on for degenerate-answer patterns a schema check can't see: invalid JSON, a placeholder value ('TBD', 'N/A', 'unknown') where a real answer should be, an array of byte-identical items (a common symptom of a loop that never advanced), or an expected field that's missing or empty.