// SCAN REPORT

LaunchFrame MCP

56 tools. 26 can modify or destroy data without limits.

4 destructive tools with no built-in limits. Policy required.

Last updated:

26 can modify or destroy data
30 read-only
56 tools total

Community server · catalogue entry verified 29/06/2026

How to control LaunchFrame MCP ↓

TOOL MAP

What LaunchFrame MCP exposes to your agents

Read (30) Write / Execute (22) Destructive / Financial (4)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS
Critical Risk

The most dangerous LaunchFrame MCP tools

Destructive · High cli_cache_clear This tool irreversibly deletes data (the local service cache) without the possibility of reversal. Destructive · Critical cli_docker_destroy This tool irreversibly destroys multiple categories of resources (containers, volumes, images, networks) and explicitly warns that local data and database volumes will be lost with no recovery option. Destructive · Critical cli_deploy_sync_features The tool explicitly truncates a production database table, which is an irreversible operation. Destructive · High cli_migration_revert Reverting a database migration undoes schema changes (dropping columns, tables, constraints) that may have already been applied to production data.

26 of LaunchFrame MCP's 56 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control LaunchFrame MCP

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

Deny destructive operations
{
  "cli_cache_clear": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
{
  "cli_cache_update": {
    "limits": [
      {
        "counter": "cli_cache_update_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "architecture_get_overview": {
    "limits": [
      {
        "counter": "architecture_get_overview_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

  1. Create a free account and register LaunchFrame MCP — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON LAUNCHFRAME →

Instant setup, no code required.

FULL CATALOGUE

All 56 LaunchFrame MCP tools

DESTRUCTIVE 4 tools
Destructive cli_cache_clear Delete the entire local LaunchFrame service cache. Services will be re-downloaded on next use. Destructive cli_deploy_sync_features Sync subscription plan features from the local database to the production database. DESTRUCTIVE: truncates sub Destructive cli_docker_destroy Destroy ALL Docker resources for a LaunchFrame project (containers, volumes, images, network). IRREVERSIBLE — Destructive cli_migration_revert Revert the most recently applied TypeORM database migration.
EXECUTE 12 tools
Execute cli_database_query cli_database_query Execute cli_deploy_build Manually build production Docker images and push to GitHub Container Registry. Optionally build a specific ser Execute cli_deploy_up Deploy the latest images to the VPS and restart all production services via SSH. Execute cli_dev_npm_install Run npm install inside a service directory using a node:20-alpine Docker container (matches the build environm Execute cli_docker_build Build Docker images for a LaunchFrame project (all services or a specific one). Execute cli_docker_down Stop all running Docker services for a LaunchFrame project. Execute cli_docker_up Start Docker services for a LaunchFrame project. Always runs detached (background). Use cli_docker_logs to ins Execute cli_migration_run Run all pending TypeORM database migrations against the local database. Execute cli_module_add Install a module into a LaunchFrame project. Runs non-interactively (skips confirmation). Rebuilds affected co Execute cli_waitlist_deploy Build and deploy the waitlist service to the VPS via SSH. Execute cli_waitlist_down Stop the locally running waitlist service. Execute cli_waitlist_up Start the waitlist service locally using Docker Compose.
WRITE 10 tools
Write cli_cache_update Force-update the local LaunchFrame service cache by re-downloading cached services. Write cli_dev_add_user Create a random test user in the local database. Generates a unique email + bcrypt password hash and inserts v Write cli_migration_create Create a new empty TypeORM migration file with the given name. Write cli_service_add Install an optional service into a LaunchFrame project. Runs non-interactively (skips prompts). Env vars will Write cron_scaffold_job Scaffold a new cron method to add to CronService (src/jobs/cron.service.ts). Write email_scaffold_send Generate NestJS code to send a transactional email — either by injecting MailService directly (direct) or via Write email_scaffold_template Generate a Handlebars (.hbs) template stub for a new LaunchFrame transactional email, following project conven Write entity_scaffold_typeorm Generate a TypeORM entity file following LaunchFrame conventions. Write module_scaffold_nestjs Generate a NestJS module scaffold (module + service + optional controller + optional entity) following LaunchF Write webhook_scaffold_handler Get a scaffold for a new webhook handler: controller receipt + Bull processor for a given provider and event t
READ 30 tools
Read architecture_get_overview Get the overall architecture of the LaunchFrame project: services, backend module layout, key patterns, fronte Read auth_get_decorator_usage Get the exact decorator and import for a specific auth need. Read auth_get_guard_usage Get the guard class, import path, and decorator combo for a specific guard type. Read auth_get_overview Get full auth system overview: guard hierarchy, session flow, Better Auth setup, roles, and decorator system. Read cli_cache_info Show information about the local LaunchFrame service cache (location, size, cached services, last update time) Read cli_docker_logs Fetch a snapshot of Docker service logs (non-streaming). Returns the last N lines. Read cli_module_list List all available modules that can be added to a LaunchFrame project (e.g., feature-flags, multi-tenancy). Read cli_service_list List all available optional services that can be added to a LaunchFrame project (e.g., waitlist, docs, custome Read cli_waitlist_logs Fetch a snapshot of waitlist service logs from the VPS (non-streaming). Returns the last N lines. Read credits_get_add_pattern Get the code snippet for programmatically adding credits to a user with a specific transaction type. Read credits_get_deduction_pattern Get the decorator + guard pattern for deducting credits on a route. Read credits_get_monetization_strategies Get an overview of all monetization strategies (free, subscription, credits, hybrid) and when to use each. Read cron_get_pattern Get the LaunchFrame cron job pattern: where jobs live, available CronExpression presets, and module registrati Read database_schema Returns the full database schema (all tables, columns, types, relations) plus ready-made SQL snippets for comm Read email_get_conventions Get an overview of the LaunchFrame email system: sending patterns (direct vs queue-based), template convention Read entity_get_conventions Get TypeORM entity conventions for LaunchFrame: required decorators, naming strategy, column types, relations, Read env_get_conventions Get environment variable conventions for LaunchFrame: single centralized .env location, variable naming rules, Read feature_gates_get_check_pattern Get a copy-paste TypeScript snippet for checking a feature gate by code and type. Read feature_gates_get_overview Get the feature gate system overview: how features are stored, how to query them, and the check pattern. Read module_get_structure Get the NestJS module folder structure, conventions, and rules used in LaunchFrame. Read queue_get_names List all available Bull queues in LaunchFrame with their purpose and usage rules. Read queue_scaffold_processor Get a Bull processor class scaffold for a given queue and job name. Read queue_scaffold_producer Get the code to inject and use a Bull queue as a producer in a NestJS service. Read rbac_get_guard_usage Get when and how to apply @RequiresPermission, owner bypass rules, cache invalidation patterns, and multi-tena Read rbac_get_overview Get full RBAC model overview: actor responsibilities, data model, default roles, guard evaluation order, and v Read rbac_get_permission_pattern Get the 4-step workflow for adding a new permission: enum → seeder → superadmin assigns → @RequiresPermission( Read subscriptions_get_plans_overview Get an overview of the subscription plans system: plan groups, annual billing toggle, API response shape, and Read variant_get_overview Get an overview of LaunchFrame project variants: Base (B2B single-tenant), Multi-tenant, and B2B2C. Explains h Read webhook_get_architecture Get an overview of the LaunchFrame webhook architecture: receipt/processing separation, WebhookLog entity, Bul
EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

Yaver 1060 tools
adminautomation
Nodebench 824 tools
adminautomation
UnClick 813 tools
adminautomation
Binance MCP Server 734 tools
adminautomation
Fortimanager 584 tools
adminautomation
Crow 573 tools
adminautomation
Mcp 571 tools
adminautomation
GoHighLevel MCP Server 566 tools
adminautomation
FAQ

Questions about LaunchFrame MCP

Can an AI agent delete data through the LaunchFrame MCP server? +

Yes. The LaunchFrame MCP server exposes 4 destructive tools including cli_cache_clear, cli_deploy_sync_features, cli_docker_destroy. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through LaunchFrame MCP? +

The LaunchFrame MCP server has 10 write tools including cli_cache_update, cli_dev_add_user, cli_migration_create. 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 LaunchFrame MCP.

How many tools does the LaunchFrame MCP server expose? +

56 tools across 4 categories: Destructive, Execute, Read, Write. 30 are read-only. 26 can modify, create, or delete data.

How do I enforce a policy on LaunchFrame MCP? +

Register the LaunchFrame 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 LaunchFrame MCP tool call.

Deterministic rules across all 56 LaunchFrame MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON LAUNCHFRAME →

Instant setup, no code required.

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

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.