add_premise · FOL Prover MCP Server MCP: Risk & Policy

WHAT IT DOES

What add_premise does on FOL Prover MCP Server

AI agents use add_premise to create or update resources in FOL Prover MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your FOL Prover MCP Server environment.

WHY IT NEEDS A POLICY

Why add_premise needs a policy

This tool creates or modifies session data by appending axioms, which is reversible (premises can be removed via clear_session or session deletion). It has no destructive, financial, or code-execution semantics. The blast radius is low because adding incorrect premises only affects proof attempts within that session and causes logical failures rather than external harm or data loss.

From the tool's definition The tool description states it "Add[s] a premise (axiom) to the current session" — this is a create/modify operation that adds data to a session state. The tool name 'add_premise' and description verb 'Add' confirm a write action.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_premise Rate-limited

add_premise 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_premise": {
      "limits": [
        {
          "counter": "add_premise_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 FOL Prover MCP Server, so you can run agents against it safely.

FAQ

Questions about add_premise

What does the add_premise tool do? +

Add a premise (axiom) to the current session for incremental proof building. It is categorised as a Write tool in the FOL Prover MCP Server 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_premise? +

Register the FOL Prover MCP Server MCP server in PolicyLayer and add a rule for add_premise: 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 FOL Prover MCP Server. Nothing to install.

What risk level is add_premise? +

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

Can I rate-limit add_premise? +

Yes. Add a rate_limit block to the add_premise 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_premise completely? +

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

add_premise is provided by the FOL Prover MCP Server MCP server (newjerseystyle/folprover-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.