按游标增量读取小说文本。输入小说名和 cursor，每次返回一到多行文本及累计字符消耗。
AI agents call read_novel_line to retrieve information from Bun Novel Processor MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a straightforward data retrieval operation. It reads novel text sequentially using a cursor mechanism, which is a read-only query pattern with no side effects. The cumulative character tracking is metadata about the read operation, not a modification of stored data. No code execution, deletion, financial transaction, or data modification occurs.
From the tool's definition Tool description indicates it 'incrementally reads novel text' (按游标增量读取小说文本) by cursor position, returning 'one or multiple lines of text and cumulative character consumption.' The tool retrieves data without modifying, deleting, or executing operations.
Attacks that exploit this kind of access
按游标增量读取小说文本。输入小说名和 cursor，每次返回一到多行文本及累计字符消耗。. It is categorised as a Read tool in the Bun Novel Processor MCP MCP Server, which means it retrieves data without modifying state.
Register the Bun Novel Processor MCP server in PolicyLayer and add a rule for read_novel_line: 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 Bun Novel Processor MCP. Nothing to install.
read_novel_line 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 read_novel_line 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 read_novel_line. 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.
read_novel_line is provided by the Bun Novel Processor MCP server (tietiezhi-1216/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 →