diagnose_errors

THE RISK

Low Risk

Why diagnose_errors needs a policy

This tool only reads and retrieves log data from the game system. It performs no write, delete, execute, or financial operations. The stub nature and incomplete implementation further confirm it is a passive read operation. Severity is low because logs typically contain non-sensitive operational information about game state, though some gaming logs might contain minor sensitive details, the risk of misuse is minimal.

From the tool's definition Tool returns raw logs without analysis or modification. Description explicitly states it 'returns raw logs' with no implemented diagnostic logic, indicating pure data retrieval with no side effects.

Documented attack patterns abuse exactly the kind of access diagnose_errors gives an agent:

POLICY

How to control diagnose_errors

PolicyLayer is an MCP gateway — it sits between your AI agents and FoundryVTT MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for diagnose_errors:

policy.json

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

diagnose_errors is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register FoundryVTT MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More FoundryVTT MCP Server tools

Destructive delete_actor_item Delete an item owned by an actor (requires FOUNDRY_WRITE_ENABLED + active Socket.IO connec Execute roll_dice Roll dice using standard RPG notation (e.g., 1d20, 3d6+4) Write create_actor_item Create an item on an actor from an inline item document (requires FOUNDRY_WRITE_ENABLED + Write generate_loot Generate random loot for encounters Write generate_npc Generate a random NPC with stats and background Write update_actor_attributes Update attributes on an actor Read get_actor_details Get detailed information about a specific actor Read get_chat_messages Get recent chat messages from the game

All 25 FoundryVTT MCP Server tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about diagnose_errors

What does the diagnose_errors tool do? +

Stub: returns raw logs without analysis. Full diagnostic logic is tracked in #133 and not yet implemented. It is categorised as a Read tool in the FoundryVTT MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on diagnose_errors? +

Register the FoundryVTT MCP Server MCP server in PolicyLayer and add a rule for diagnose_errors: 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 FoundryVTT MCP Server. Nothing to install.

What risk level is diagnose_errors? +

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

Can I rate-limit diagnose_errors? +

Yes. Add a rate_limit block to the diagnose_errors 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 diagnose_errors completely? +

Set action: deny in the PolicyLayer policy for diagnose_errors. 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 diagnose_errors? +

diagnose_errors is provided by the FoundryVTT MCP Server MCP server (laurigates/foundryvtt-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every FoundryVTT MCP Server tool call.

Start from FoundryVTT MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →