// SCAN REPORT

Cakesmash

4 tools. 0 can modify or destroy data without limits.

Read-only server. Low risk, but rate limits prevent runaway API costs.

Last updated: 12 Jun 2026

0 can modify or destroy data

4 read-only

4 tools total

Community server · catalogue entry verified 12/06/2026 · full schemas captured for 3 of 4 tools

How to control Cakesmash ↓

TOOL MAP

What Cakesmash exposes to your agents

Read (4) Write / Execute (0) Destructive / Financial (0)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Cakesmash costs in tokens

728 tokens of tool definitions, loaded on every request

0.4% of a 200k context window

279 heaviest tool: get_reel_script_sample

Full per-tool breakdown → Model it in the token calculator →

THE RISK

What can go wrong

Even read-only tools carry cost. An agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up bills.

POLICY

How to control Cakesmash

PolicyLayer is an MCP gateway — it sits between your AI agents and Cakesmash, and nothing reaches the server without passing your rules. These are the rules we recommend:

Cap read operations

{
  "find_pack": {
    "limits": [
      {
        "counter": "find_pack_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Cakesmash — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON CAKESMASH →

Free to start. No card required.

FULL CATALOGUE

All 4 Cakesmash tools

READ 4 tools

Read find_pack Given a description of a medical or dental practice type, returns the matching Cakesmash script pack with titl Read get_hook_examples Returns a small number of opening hook examples (the first 3 seconds of a reel — the line that stops the scrol Read get_pulse_diagnostic Returns the Cakesmash P.U.L.S.E. Framework™ — a 5-question self-diagnostic that helps a medical or dental prac Read get_reel_script_sample Returns one full sample Instagram/TikTok reel script for a medical or dental practice niche. Each script inclu

FAQ

Questions about Cakesmash

Is the Cakesmash MCP server safe to use without restrictions? +

The Cakesmash server is primarily read-only with 4 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the Cakesmash MCP server expose? +

4 tools across 1 categories: Read. 4 are read-only. 0 can modify, create, or delete data.

How do I enforce a policy on Cakesmash? +

Register the Cakesmash MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Cakesmash tool call.

Deterministic rules across all 4 Cakesmash tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CAKESMASH →

Free to start. No card required.

4 Cakesmash tools catalogued and risk-classified — across an index of 43,000+ MCP servers.