从EPUB文件中提取文本内容
AI agents call epub_extract_text to retrieve information from Epub Parser without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and extracts text from EPUB documents, a read-only operation. It has no side effects—it does not modify files, execute code, delete data, or trigger external operations. The sibling tools (epub_info, epub_search, epub_toc) follow the same pattern of passive data extraction.
From the tool's definition Tool name 'epub_extract_text' and description '从EPUB文件中提取文本内容' (extract text content from EPUB files) indicate pure data retrieval with no modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
从EPUB文件中提取文本内容. It is categorised as a Read tool in the Epub Parser MCP Server, which means it retrieves data without modifying state.
Register the Epub Parser MCP server in PolicyLayer and add a rule for epub_extract_text: 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 Epub Parser. Nothing to install.
epub_extract_text 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 epub_extract_text 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 epub_extract_text. 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.
epub_extract_text is provided by the Epub Parser MCP server (kala51773/epub-parser-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 →