extend_schema · Advanced Prompting Engine MCP: Risk & Policy

WHAT IT DOES

What extend_schema does on Advanced Prompting Engine

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

WHY IT NEEDS A POLICY

Why extend_schema needs a policy

This tool creates or modifies data (graph constructs and relations) in a reversible manner. Users can add new philosophical constructs to the schema, but these additions are not inherently destructive—they extend rather than delete. The 'contradiction detection' feature is automatic validation, not a destructive operation.

From the tool's definition Tool description states 'Add constructs or relations to the graph' - the verb 'add' indicates creation/modification of data within the philosophical framework. The graph structure is being extended with new entries.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

extend_schema Rate-limited

extend_schema 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": {
    "extend_schema": {
      "limits": [
        {
          "counter": "extend_schema_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 Advanced Prompting Engine, so you can run agents against it safely.

FAQ

Questions about extend_schema

What does the extend_schema tool do? +

Add constructs or relations to the graph. Contradiction detection is automatic. It is categorised as a Write tool in the Advanced Prompting Engine MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on extend_schema? +

Register the Advanced Prompting Engine MCP server in PolicyLayer and add a rule for extend_schema: 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 Advanced Prompting Engine. Nothing to install.

What risk level is extend_schema? +

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

Can I rate-limit extend_schema? +

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

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

extend_schema is provided by the Advanced Prompting Engine MCP server (joshuaramirez/advanced-prompting-engine). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.