promptthrift_count_tokens
AI agents call promptthrift_count_tokens to retrieve information from PromptThrift MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Token counting is a read-only operation that analyzes and reports metrics on input data. It retrieves information about token usage but does not execute code, modify data, delete resources, or trigger external operations. The absence of side effects and the analytical nature of the operation place this firmly in the Read category with low severity.
From the tool's definition Tool name 'promptthrift_count_tokens' indicates token counting functionality. The server description mentions 'token counting' as a feature for analyzing conversation history without modifying it. No side effects or modifications occur.
Attacks that exploit this kind of access
promptthrift_count_tokens. It is categorised as a Read tool in the PromptThrift MCP MCP Server, which means it retrieves data without modifying state.
Register the PromptThrift MCP server in PolicyLayer and add a rule for promptthrift_count_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 PromptThrift MCP. Nothing to install.
promptthrift_count_tokens 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 promptthrift_count_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.
Set action: deny in the PolicyLayer policy for promptthrift_count_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.
promptthrift_count_tokens is provided by the PromptThrift MCP server (woling-dev/promptthrift-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →