check_goal

Evaluate whether the active goal is fully met. Call at the end of every turn with a concrete

Server Goal Engine melihzafer/mcp-goal
Category Read
Risk class Low
Parameters 00 required

What check_goal does on Goal Engine

AI agents call check_goal to retrieve information from Goal Engine without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why check_goal needs a policy

This tool reads goal status and performs evaluation logic, returning a boolean or status result. It has no side effects, does not create, modify, or delete data, and does not execute arbitrary code or financial operations. It is a read-only query mechanism for an agentic loop control flow.

From the tool's definition Tool name 'check_goal' and description indicate it 'Evaluate[s] whether the active goal is fully met' — a query operation that retrieves and assesses the status of an existing goal without modifying state.

Risk signalsBulk/mass operation — affects multiple targets

Questions about check_goal

What does the check_goal tool do? +

Evaluate whether the active goal is fully met. Call at the end of every turn with a concrete. It is categorised as a Read tool in the Goal Engine MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on check_goal? +

Register the Goal Engine MCP server in PolicyLayer and add a rule for check_goal: 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 Goal Engine. Nothing to install.

What risk level is check_goal? +

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

Can I rate-limit check_goal? +

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

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

check_goal is provided by the Goal Engine MCP server (melihzafer/mcp-goal). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER SERVER

Every MCP server has a record like this.

Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.