cort.think.details

THE RISK

Low Risk

Why cort.think.details needs a policy

The description is empty, so there is no direct evidence of what this tool does. Based on the server context (Chain-of-Recursive-Thoughts reasoning) and sibling tools, this tool likely performs internal AI reasoning/thinking operations with no external side effects — no data is read from external sources, written, executed, or deleted. It appears to be a cognitive/processing tool that returns reasoning details.

From the tool's definition Tool description is empty and uninformative; tool name 'cort.think.details' suggests a thinking/reasoning operation based on the server's CoRT methodology

Documented attack patterns abuse exactly the kind of access cort.think.details gives an agent:

POLICY

How to control cort.think.details

PolicyLayer is an MCP gateway — it sits between your AI agents and CoRT MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for cort.think.details:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "cort.think.details": {
      "limits": [
        {
          "counter": "cort.think.details_rate",
          "window": "minute",
          "max": 60,
          "scope": "grant"
        }
      ]
    }
  }
}

cort.think.details gets a rate cap, and everything else on the server is denied unless you say otherwise.

Create a free account and register CoRT MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

SET A RULE FOR THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More CoRT MCP Server tools

Execute cort.think.details_mixed_llm Generate recursive thinking AI response with full history, using a different LLM (provider Execute cort.think.simple_mixed_llm Generate recursive thinking AI response using a different LLM (provider/model) for each al Read cort.think.details_mixed_llm.neweval cort.think.details_mixed_llm.neweval Other cort.think.details.neweval cort.think.details.neweval Other cort.think.simple cort.think.simple Other cort.think.simple_mixed_llm.neweval cort.think.simple_mixed_llm.neweval Other cort.think.simple.neweval cort.think.simple.neweval

All 8 CoRT MCP Server tools →

Other tools on other servers

Android Forensics ADB MCP Server generate_app_analysis_report Ethereum Tools add Math MCP Server complex_analysis_suite Crypto_MCP aes_encrypt

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Tool risk categories → How PolicyLayer classifies MCP tools by what they can do.
MCP tool → What an MCP tool is and how clients discover and call it.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about cort.think.details

What does the cort.think.details tool do? +

cort.think.details. It is categorised as a Other tool in the CoRT MCP Server MCP Server, which means it performs auxiliary operations.

How do I enforce a policy on cort.think.details? +

Register the CoRT MCP Server MCP server in PolicyLayer and add a rule for cort.think.details: 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 CoRT MCP Server. Nothing to install.

What risk level is cort.think.details? +

cort.think.details is a Other tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit cort.think.details? +

Yes. Add a rate_limit block to the cort.think.details 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 cort.think.details completely? +

Set action: deny in the PolicyLayer policy for cort.think.details. 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 cort.think.details? +

cort.think.details is provided by the CoRT MCP Server MCP server (kunihiros/cort-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every CoRT MCP Server tool call.

Start from CoRT MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →