// SCAN REPORT

Launch Engine

3 tools. 3 can modify or destroy data without limits.

3 write tools that can modify data. Rate limits recommended.

Last updated: 29 Jun 2026

3 can modify or destroy data

0 read-only

3 tools total

Community server · catalogue entry verified 29/06/2026

How to control Launch Engine ↓

TOOL MAP

What Launch Engine exposes to your agents

Read (0) Write / Execute (3) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Launch Engine tools

Write · Medium capture_learning Capture a reusable learning/pattern to learnings.json. Called after key decisions, verdicts, and pipeline milestones. Write · Medium save_asset Save a file to the assets/[market-name]/ directory. Use for all pipeline outputs: research, building blocks, copy, campaigns, etc. Write · Medium update_pipeline_state Update pipeline-state.json. Use dot-notation paths to set values. Can create new pipelines and rapid tests.

3 of Launch Engine's 3 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Launch Engine

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

Rate limit write operations

{
  "capture_learning": {
    "limits": [
      {
        "counter": "capture_learning_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Create a free account and register Launch Engine — 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 LAUNCH ENGINE →

Instant setup, no code required.

FULL CATALOGUE

All 3 Launch Engine tools

WRITE 3 tools

Write capture_learning Capture a reusable learning/pattern to learnings.json. Called after key decisions, verdicts, and pipeline mile Write save_asset Save a file to the assets/[market-name]/ directory. Use for all pipeline outputs: research, building blocks, c Write update_pipeline_state Update pipeline-state.json. Use dot-notation paths to set values. Can create new pipelines and rapid tests.

FAQ

Questions about Launch Engine

How do I prevent bulk modifications through Launch Engine? +

The Launch Engine server has 3 write tools including capture_learning, save_asset, update_pipeline_state. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Launch Engine.

How many tools does the Launch Engine MCP server expose? +

3 tools across 1 categories: Write. 0 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on Launch Engine? +

Register the Launch Engine 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 Launch Engine tool call.

Deterministic rules across all 3 Launch Engine tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON LAUNCH ENGINE →

Instant setup, no code required.

3 Launch Engine tools catalogued and risk-classified — across an index of 43,000+ MCP servers.