AI agents call get_token_count to retrieve information from Web Scraper without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a computational analysis of text to estimate token counts, which is a retrieval/analysis function with no side effects, no external code execution, and no data modification. It is clearly a Read category tool with low severity since misuse would only return inaccurate token estimates, causing no operational harm.
From the tool's definition Tool name 'get_token_count' and description 'Estimate token count for text' indicate a read-only operation that analyzes and returns metadata about input text without modifying, executing, or deleting anything.
Documented attack patterns abuse exactly the kind of access get_token_count gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Web Scraper, and nothing reaches the server without passing your rules. This is the rule we recommend for get_token_count:
{
"version": "1",
"default": "deny",
"tools": {
"get_token_count": {}
}
}get_token_count is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Estimate token count for text. It is categorised as a Read tool in the Web Scraper MCP Server, which means it retrieves data without modifying state.
Register the Web Scraper MCP server in PolicyLayer and add a rule for get_token_count: 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 Web Scraper. Nothing to install.
get_token_count 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 get_token_count 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 get_token_count. 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.
get_token_count is provided by the Web Scraper MCP server (imyourboyroy/webscrapertoolkit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Web Scraper, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
62 Web Scraper tools catalogued and risk-classified — across an index of 43,000+ MCP servers.