Skip to content

ApproveKit MCP server

dev.approvekit/approvekitapprovekit.devstreamable-httpv0.1.0Scanned

Audit apps against App Store, Google Play and Google OAuth review rules; get the required docs.

4 tools: 1 do something that can't be undone, 2 change things and 1 only read.

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

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here does something that can't be undone. Govern it.

  • 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 ApproveKit MCP server can do

The ApproveKit MCP server is published by approvekit.dev, a domain the MCP Registry verified. It has 4 tools. It can do things that cannot be undone, such as sending, paying or publishing (publish_document) and create or change data (2 tools: audit_app and create_checkout), but cannot delete data. 1 tool only reads.

2 tools bring in text other people can write (create_checkout and get_order); 1 tool can send data out of your system (publish_document).

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 0.1.0.

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.

4 tools

Can't be undone 1Claude Code: ask
  • publish_documentSaves the final version of a document after every [CONFIRM: ...] placeholder has been resolved with the user.Can send data outNo findings

    Why it is in this group

    • The name "publish_document" says "publish": a word for a change that another call does not undo.

    What it can reach

    • outboundThe name "publish_document" says "publish": it sends or publishes something to other people.
    Description, as the server wrote it
    Saves the final version of a document after every [CONFIRM: ...] placeholder has been resolved with the user. For privacy-policy and account-deletion this makes the hosted page live at its public URL; for the other kinds it just stores the final text. Call it again whenever the text needs an update (for example after the app adds a new data type).

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Changes things 2Claude Code: ask
  • audit_appUse before submitting a mobile or web app to the Apple App Store, Google Play or Google OAuth verification.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Use before submitting a mobile or web app to the Apple App Store, Google Play or Google OAuth verification. Pass an inventory of what the app collects, which SDKs it uses and which Google scopes it requests (build it by reading the repo). Returns the problems reviewers are likely to reject, how to fix each one, and which paid package generates the missing documents. Free. The first call returns an app_token: save it in .approvekit.json at the project root and pass it on later calls so the app is updated instead of duplicated.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • create_checkoutCreates a Stripe Checkout link for one app.Reads text others writeNo findings

    Why it is in this group

    • The name "create_checkout" says "create": a word for a change.

    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
    Creates a Stripe Checkout link for one app. Only call this after the user agreed to the purchase. Show the link to the user so they can pay; then call get_order with the returned order_id to receive the documents.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Only reads 1Show 1 read-only tool
  • get_orderReturns the payment status of an order.Reads text others writeNo findings

    Why it is in this group

    • The name "get_order" says "get": 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
    Returns the payment status of an order. Once paid, returns every generated document as Markdown plus the public URLs of the hosted privacy policy and account deletion pages, ready to paste into App Store Connect, Play Console or the Google OAuth consent screen.

    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.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write2
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
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 20, 2026, 18:51 UTC, unchanged since Oct 22, 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
3
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
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 3 tools that change things (1 irreversible, 2 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://approvekit.dev/mcp: tools/list returned 4 tools to an anonymous client, including publish_document (irreversible), audit_app (write), create_checkout (write)

    What this check looks for

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 0.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http approvekit https://approvekit.dev/mcp
claude mcp add --transport http approvekit https://approvekit.dev/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__approvekit__get_order"
    ],
    "ask": [
      "mcp__approvekit__audit_app",
      "mcp__approvekit__create_checkout",
      "mcp__approvekit__publish_document"
    ],
    "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 approvekit. Review it before you use it.

Capability tags behind 3 rules
  • mcp__approvekit__create_checkout untrusted-input
  • mcp__approvekit__get_order untrusted-input
  • mcp__approvekit__publish_document outbound

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/dev.approvekit/approvekit/verify?hash=445e65581e9c6ad75298dbff633c61768a7e6e292072a7241511bb25094dd378" | jq -e '.changed == false'

Pinned hash 445e65581e9c, from Nov 11, 2026, 07:18 UTC.

Watch

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

https://radar.anlyon.com/servers/dev.approvekit/approvekit/changes.xml

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

Badge

Anlyon Radar badge for dev.approvekit/approvekit
[![Anlyon Radar](https://radar.anlyon.com/badge/dev.approvekit/approvekit.svg)](https://radar.anlyon.com/servers/dev.approvekit/approvekit)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:11 UTC.

ApproveKit MCP server: questions and answers

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

Is the ApproveKit MCP server safe?

No scan can promise that. What its definitions show: 4 tools, 3 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the ApproveKit MCP server delete data?

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

Can the ApproveKit MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: publish_document.

What tools does the ApproveKit MCP server have?

4 tools: 1 irreversible, 2 write, 1 read. publish_document, audit_app, create_checkout and get_order.

Does the ApproveKit MCP server need sign-in or OAuth?

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

Does the ApproveKit MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): publish_document.

Has the ApproveKit MCP server changed its tools?

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