ファイルの単語数を計測します。絶対パスを指定してください（Windows形式 C:\\Users\\...、またはWSL/Linux形式 /c/Users/... のどちらも可）。英語ではスペースで区切られた単語をカウントし、日本語では形態素解析を使用します。
AI agents call count_words 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.
The tool performs read-only analysis of file contents to extract word count statistics. While it requires a file path as input, it neither modifies the file, executes code, deletes data, nor triggers external operations. The functionality is purely informational retrieval with no side effects beyond returning a count metric.
From the tool's definition Tool description states it "counts words" (単語数を計測します) in files by reading them with morphological analysis for Japanese and space-based tokenization for English. No modification, deletion, execution, or financial operations are mentioned or implied.
Attacks that exploit this kind of access
ファイルの単語数を計測します。絶対パスを指定してください（Windows形式 C:\\Users\\...、またはWSL/Linux形式 /c/Users/... のどちらも可）。英語ではスペースで区切られた単語をカウントし、日本語では形態素解析を使用します。. 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_words: 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_words 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_words 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_words. 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_words 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 →