テキストの文字数を計測します。スペースや改行を除いた実質的な文字数をカウントします。
AI agents call count_clipboard_chars to retrieve information from Japanese Text Analyzer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a purely analytical tool that reads clipboard content and counts characters. It has no side effects—it does not modify data, execute code, delete anything, or trigger external operations. It falls clearly into the Read category with low severity, as misuse poses minimal risk (an agent could only obtain character counts from clipboard data, which is inherently visible to the user anyway).
From the tool's definition Tool description states it 'テキストの文字数を計測します' (counts the number of characters in text) and performs analysis without modification.
Attacks that exploit this kind of access
テキストの文字数を計測します。スペースや改行を除いた実質的な文字数をカウントします。. It is categorised as a Read tool in the Japanese Text Analyzer MCP Server, which means it retrieves data without modifying state.
Register the Japanese Text Analyzer MCP server in PolicyLayer and add a rule for count_clipboard_chars: 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 Japanese Text Analyzer. Nothing to install.
count_clipboard_chars 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_clipboard_chars 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_clipboard_chars. 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_clipboard_chars is provided by the Japanese Text Analyzer MCP server (mistizz/mcp-japanesetextanalyzer). 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 →