evaluate_action

Preview the policy decision for an intended action. Returns allowed, limited, approval, or forbidden. This preview is not an audit record; use record_decision before acting.

SERVERLaguarde SOURCElaguarde-mcp

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade B, identity unverified Pull the record →

This record as markdown: /tools/dev-futur-panda-laguarde/evaluate-action.md

WHAT IT DOES

What evaluate_action does on Laguarde

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

RISK

Why evaluate_action is rated Low

Tool reads and returns policy decisions without modifying state or executing actions.

From the tool's definition Preview the policy decision for an intended action. Returns allowed, limited, approval, or forbidden.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs evaluate_action safely

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

evaluate_action Allowed

evaluate_action 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": {
    "evaluate_action": {}
  }
}

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

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

FAQ

Questions about evaluate_action

What does the evaluate_action tool do? +

Preview the policy decision for an intended action. Returns allowed, limited, approval, or forbidden. This preview is not an audit record; use record_decision before acting. It is categorised as a Read tool in the Laguarde MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on evaluate_action? +

Register the Laguarde MCP server in PolicyLayer and add a rule for evaluate_action: 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 Laguarde. Nothing to install.

What risk level is evaluate_action? +

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

Can I rate-limit evaluate_action? +

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

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

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

KEEP EXPLORING

More on Laguarde, and thousands of servers like it.

This server

All 5 Laguarde tools →

Across the catalogue

The MCP Attack Database →

Guides

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