backend_detect

SERVERBreakpoint SOURCEbreakpoint-mcp

Low RISK CLASS

Category Read

Parameters 10 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/breakpoint-mcp/backend-detect.md

WHAT IT DOES

What backend_detect does on Breakpoint

AI agents call backend_detect to retrieve information from Breakpoint without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Parameter	Type	Required	Description
`sdk`	string	—	Focus the report on a single SDK (default: report all four)

Parameters from the server's own tool schema.

RISK

Why backend_detect is rated Low

Even though backend_detect only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs backend_detect safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Breakpoint, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For backend_detect, this is the rule to start with:

backend_detect Allowed

backend_detect is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "backend_detect": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Breakpoint, apply this rule, and every backend_detect call is checked against it from then on.

FAQ

Questions about backend_detect

What does the backend_detect tool do? +

Report which of the known game-backend SDKs (SilentWolf, Nakama, PlayFab, Photon) are installed in this project and how each was found (an enabled autoload, an addon directory under res://addons, or a global class_name). Read-only — nothing is written. Use it before backend_configure / *_scaffold to see what you can generate against. It is categorised as a Read tool in the Breakpoint MCP Server, which means it retrieves data without modifying state.

What parameters does backend_detect accept? +

backend_detect accepts 1 parameter: sdk. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on backend_detect? +

Register the Breakpoint MCP server in PolicyLayer and add a rule for backend_detect: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Breakpoint. Nothing to install.

What risk level is backend_detect? +

backend_detect is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit backend_detect? +

Yes. Add a rate_limit block to the backend_detect rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block backend_detect completely? +

Set action: deny in the PolicyLayer policy for backend_detect. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides backend_detect? +

backend_detect is provided by the Breakpoint MCP server (breakpoint-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Breakpoint, and thousands of servers like it.

This server

All 280 Breakpoint tools →

Across the catalogue

The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →