get_thinking

Retrieve a thinking process

SERVERNcp SOURCE@portel/ncp

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-portel-dev-ncp/get-thinking.md

WHAT IT DOES

What get_thinking does on Ncp

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

RISK

Why get_thinking is rated Low

The verb 'Retrieve' combined with 'Retrieve a thinking process' clearly describes a data retrieval operation. No modification, deletion, code execution, or financial action is indicated. This falls squarely into the Read category with low severity, as retrieving cached or stored thinking does not alter system state or risk significant harm if misused.

From the tool's definition Tool name and description indicate 'Retrieve a thinking process' — a read-only operation that queries or fetches data with no side effects.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs get_thinking safely

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

get_thinking Allowed

get_thinking 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": {
    "get_thinking": {}
  }
}

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

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

FAQ

Questions about get_thinking

What does the get_thinking tool do? +

Retrieve a thinking process. It is categorised as a Read tool in the Ncp MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_thinking? +

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

What risk level is get_thinking? +

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

Can I rate-limit get_thinking? +

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

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

get_thinking is provided by the Ncp MCP server (@portel/ncp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Ncp, and thousands of servers like it.

This server

All 275 Ncp tools →

Across the catalogue

get_cocktail_by_category on Cocktails RAG MCP Server →get_torrent_detail on M-Team MCP Server →aiva_get_affiliate on AIVA MCP Server →get-chuck-categories on Jokes MCP Server → The MCP Attack Database →

Guides

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