Count the number of tokens in a text string for the configured Gemini model. Use this tool to: - Estimate prompt costs before making queries - Ensure prompts fit within model context limits - Optimize prompt length for efficiency
AI agents call count_gemini_tokens to retrieve information from Gemini MCP Server for Claude Code without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that queries token count information from the Gemini model's tokenizer. It retrieves data without creating, modifying, deleting, or executing any external operations. The blast radius of misuse is minimal: an agent could only waste API quota by over-calling the tool, but cannot damage data or systems.
From the tool's definition The tool 'count_gemini_tokens' counts tokens in text without modifying, deleting, or executing any operations.
Attacks that exploit this kind of access
Count the number of tokens in a text string for the configured Gemini model. Use this tool to: - Estimate prompt costs before making queries - Ensure prompts fit within model context limits - Optimize prompt length for efficiency. It is categorised as a Read tool in the Gemini MCP Server for Claude Code MCP Server, which means it retrieves data without modifying state.
Register the Gemini MCP Server for Claude Code MCP server in PolicyLayer and add a rule for count_gemini_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 Gemini MCP Server for Claude Code. Nothing to install.
count_gemini_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 count_gemini_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 count_gemini_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.
count_gemini_tokens is provided by the Gemini MCP Server for Claude Code MCP server (raydollete/gemini-for-claude-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 →