Skip to content
ShipLatch logo

ShipLatch MCP server

Which MCP servers are ShipLatch's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-28

← Back to ShipLatch

Whose server it is
  • Registry namecom.shiplatch/scannerverified in the MCP registry

The registry name sits under shiplatch.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-28
  • Stateanswerschecked 2026-10-28
  • Tools3
  • Server calls itselfShipLatch
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 184 ms.

Should an agent connect itNot proven either way yet
  • Its tools do Scan a live site for leaked API keys; Find exposed env and git files on a public site, but not Check Supabase row-level security before launch.
  • Checked on 6 of the 7 days it takes to judge reliability.

Once connected

  • For "Scan a live site for leaked API keys", the likely first call is scan_url.
  • For "Find exposed env and git files on a public site", the likely first call is scan_url.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 6, the first on 2026-10-28
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 6 so far
  • What an agent can do with it2 of 3 use cases
  • Answeredmeasuring6 of the 7 daily checks it takes to print a share
  • Median first answer219 ms
  • Space in an agent's context≈ 428 tokensthe definitions of all its tools (3), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results0 of 3 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • can do · Scan a live site for leaked API keys
  • can do · Find exposed env and git files on a public site
  • cannot · Check Supabase row-level security before launch

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers3 tools · read 2026-10-28
  • scan_url

    Run ShipLatch's free passive security scan on a public web app URL (for example a Lovable, Bolt, Replit or Cursor app). Read-only: it fetches the page and its public JS like a browser would and never logs in, submits forms or tests…

  • get_scan

    Get the free summary of a ShipLatch scan by its scan_ref (from scan_url). Use it when scan_url returned status "running". Results are kept for 7 days.

  • list_checks

    List the categories of security checks ShipLatch runs, which are in the free passive scan and which need ownership verification. No network access.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "scanner": {
      "type": "http",
      "url": "https://shiplatch.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http shiplatch https://shiplatch.com/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://shiplatch.com/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.