tokens

Token usage and savings from Code-Mode vs find+run. Shows efficiency gains.

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/tokens.md

WHAT IT DOES

What tokens does on Ncp

AI agents call tokens 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 tokens is rated Low

The tool appears to read and display token usage statistics and efficiency comparisons between Code-Mode and find+run operations. This is a reporting/analytics read operation with no side effects. Confidence is slightly reduced because the description is brief and the tool name 'tokens' is ambiguous (could relate to auth tokens), but the description context points clearly to usage metrics.

From the tool's definition 'Token usage and savings' and 'Shows efficiency gains' indicate this tool retrieves and displays metrics/statistics

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs tokens 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 tokens, this is the rule to start with:

tokens Allowed

tokens 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": {
    "tokens": {}
  }
}

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 tokens call is checked against it from then on.

FAQ

Questions about tokens

What does the tokens tool do? +

Token usage and savings from Code-Mode vs find+run. Shows efficiency gains. 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 tokens? +

Register the Ncp MCP server in PolicyLayer and add a rule for tokens: 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 tokens? +

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

Can I rate-limit tokens? +

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

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

tokens 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

The MCP Attack Database →

Guides

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