add_failure · Faulkner DB MCP: Risk & Policy

WHAT IT DOES

What add_failure does on Faulkner DB

AI agents use add_failure to create or update resources in Faulkner DB — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Faulkner DB environment.

WHY IT NEEDS A POLICY

Why add_failure needs a policy

This tool creates or writes new failure records to a temporal knowledge graph database. While 'add_failure' creates data reversibly (failures can presumably be queried, updated, or removed via other tools), it is a Write-category operation.

From the tool's definition Tool name 'add_failure' and partial description 'Document what didn' indicate a tool that creates or records new data entries (failures) in the knowledge graph system.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_failure Rate-limited

add_failure stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "add_failure": {
      "limits": [
        {
          "counter": "add_failure_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Faulkner DB, so you can run agents against it safely.

FAQ

Questions about add_failure

What does the add_failure tool do? +

Document what didn. It is categorised as a Write tool in the Faulkner DB MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_failure? +

Register the Faulkner DB MCP server in PolicyLayer and add a rule for add_failure: 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 Faulkner DB. Nothing to install.

What risk level is add_failure? +

add_failure is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit add_failure? +

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

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

add_failure is provided by the Faulkner DB MCP server (platano78/faulkner-db). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.