tokencount_estimate
Estimate token counts for text across different LLM tokenizers (GPT-4, Claude, WordPiece).
This record as markdown: /tools/io-github-malamutemayhem-unclick-mcp-server/tokencount-estimate.md
What tokencount_estimate does on UnClick
AI agents call tokencount_estimate to retrieve information from UnClick without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
text | string | Yes | Text to estimate tokens for. |
Parameters from the server's own tool schema.
Why tokencount_estimate is rated Low
This is a stateless computational utility that analyzes text input and returns token count estimates. It performs no destructive, financial, write, or execute operations; it merely reads input text and returns analytical results. The blast radius of misuse is minimal—an agent could at worst generate spurious token estimates, causing no real harm to systems or data.
From the tool's definition Tool name and description indicate it 'estimate[s] token counts for text' across different tokenizers—a pure information retrieval operation with no side effects, data modifications, or external state changes.
Attacks that exploit this kind of access
The rule that runs tokencount_estimate safely
PolicyLayer is an MCP gateway: it sits between your AI agents and UnClick, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For tokencount_estimate, this is the rule to start with:
tokencount_estimate is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect UnClick, apply this rule, and every tokencount_estimate call is checked against it from then on.
Questions about tokencount_estimate
Estimate token counts for text across different LLM tokenizers (GPT-4, Claude, WordPiece). It is categorised as a Read tool in the UnClick MCP Server, which means it retrieves data without modifying state.
tokencount_estimate accepts 1 parameter: text. Required: text. The full parameter table on this page comes from the server's own tool schema.
Register the UnClick MCP server in PolicyLayer and add a rule for tokencount_estimate: 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 UnClick. Nothing to install.
tokencount_estimate is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the tokencount_estimate 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.
Set action: deny in the PolicyLayer policy for tokencount_estimate. 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.
tokencount_estimate is provided by the UnClick MCP server (@unclick/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on UnClick, and thousands of servers like it.
This server
Across the catalogue