Skip to content

Fireshift Leak Score MCP server

ai.fireshift/leak-scorefireshift.aistreamable-httpv1.0.0Scanned

Scores a website's Google Ads and GA4 conversion setup from its public tags and lists the leaks.

2 tools: 2 only read.

Tools: 0 delete, 0 irreversible, 0 write, 2 read.
  • Reads private data · 0
  • Reads text others write · 1
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

Decide which of this server's tools your agent can use.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the Fireshift Leak Score MCP server can do

The Fireshift Leak Score MCP server is published by fireshift.ai, a domain the MCP Registry verified. It has 2 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.

1 tool brings in text other people can write (scan_site).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 11, 2026, version 1.0.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

2 tools

Only reads 2Show 2 read-only tools
  • get_statsReturns aggregate counts from scans run on fireshift.ai and through this server: total scans, distinct sites, scans in the last 7 days, the most common findings in the last 7 days …No findings

    Why it is in this group

    • The name "get_stats" says "get": a word for reading.
    Description, as the server wrote it
    Returns aggregate counts from scans run on fireshift.ai and through this server: total scans, distinct sites, scans in the last 7 days, the most common findings in the last 7 days with their share of scored sites, and the grade mix. Never returns domain names. Updated every 5 minutes.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • scan_siteReads the public homepage of a domain, finds its Google Tag Manager and Google tag container IDs, loads those containers from googletagmanager.com and scores the conversion setup f…Reads text others writeNo findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Reads the public homepage of a domain, finds its Google Tag Manager and Google tag container IDs, loads those containers from googletagmanager.com and scores the conversion setup from 0 to 100 (grade A to F). Findings include Google Ads conversions that fire on every page load, on plain page views, on login, on button clicks or when a trial ends, GA4 key events on page_view, duplicate conversions, conversions without a value, and more than one GA4 property. Same checks and score as https://fireshift.ai/scan/. Reads only what the site serves publicly; no login, no forms. It cannot see whether an Ads conversion is primary or secondary. Tags loaded server-side or only after cookie consent are not visible, so a site with no public container gets no score. Takes 2 to 20 seconds.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write1
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 19, 2026, 17:20 UTC, unchanged since Nov 12, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
0
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http leak-score https://mcp.fireshift.ai/mcp
claude mcp add --transport http leak-score https://mcp.fireshift.ai/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__leak-score__scan_site",
      "mcp__leak-score__get_stats"
    ],
    "ask": [],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as leak-score. Review it before you use it.

Capability tags behind 1 rule
  • mcp__leak-score__scan_site untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/ai.fireshift/leak-score/verify?hash=6f1d2024517f2032e92b5d9fb72571dd852e94563a87aa7f5e2105a5efc7acdb" | jq -e '.changed == false'

Pinned hash 6f1d2024517f, from Nov 11, 2026, 18:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/ai.fireshift/leak-score/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for ai.fireshift/leak-score
[![Anlyon Radar](https://radar.anlyon.com/badge/ai.fireshift/leak-score.svg)](https://radar.anlyon.com/servers/ai.fireshift/leak-score)

Source: MCP Registry. Synced Nov 11, 2026, 18:17 UTC.

Fireshift Leak Score MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Fireshift Leak Score MCP server safe?

No scan can promise that. What its definitions show: 2 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.

Can the Fireshift Leak Score MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Fireshift Leak Score MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the Fireshift Leak Score MCP server have?

2 tools: 2 read. scan_site and get_stats.

Does the Fireshift Leak Score MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Fireshift Leak Score MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Fireshift Leak Score MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 11, 2026.