util_token_estimate
Estimate token count for text. Uses word/4 heuristic (GPT-family) and char/4 (Claude-family).
This record as markdown: /tools/io-github-davidmosiah-delx-protocol/util-token-estimate.md
What util_token_estimate does on Delx Protocol — Agent Recovery & Continuity
AI agents call util_token_estimate to retrieve information from Delx Protocol — Agent Recovery & Continuity 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 |
model | string | — | Optional model hint: gpt-4, claude-3, etc. |
Parameters from the server's own tool schema.
Why util_token_estimate is rated Low
This is a read-only tool that performs a lightweight computation on provided text to estimate token counts. It retrieves no sensitive data, has no side effects, and returns only a numerical estimate. The blast radius of misuse is minimal: an attacker could only obtain token count estimates, which provides negligible value or harm in isolation.
From the tool's definition Tool description states it 'Estimate[s] token count for text' using heuristic calculations. No modifications to data, no code execution, no financial impact, no destructive operations—purely a query/calculation utility.
Attacks that exploit this kind of access
The rule that runs util_token_estimate safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Delx Protocol — Agent Recovery & Continuity, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For util_token_estimate, this is the rule to start with:
util_token_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 Delx Protocol — Agent Recovery & Continuity, apply this rule, and every util_token_estimate call is checked against it from then on.
Questions about util_token_estimate
Estimate token count for text. Uses word/4 heuristic (GPT-family) and char/4 (Claude-family). It is categorised as a Read tool in the Delx Protocol — Agent Recovery & Continuity MCP Server, which means it retrieves data without modifying state.
util_token_estimate accepts 2 parameters: text, model. Required: text. The full parameter table on this page comes from the server's own tool schema.
Register the Delx Protocol — Agent Recovery & Continuity MCP server in PolicyLayer and add a rule for util_token_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 Delx Protocol — Agent Recovery & Continuity. Nothing to install.
util_token_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 util_token_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 util_token_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.
util_token_estimate is provided by the Delx Protocol — Agent Recovery & Continuity MCP server (https://api.delx.ai/v1/mcp?src=registry). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Delx Protocol — Agent Recovery & Continuity, and thousands of servers like it.
Across the catalogue