Read one chunk of a large text file (e.g. a book) that was pre-split into ~3000-word chunks by book_split. Use iteratively to read through a whole document that does not fit in the context window. Returns the chunk text plus metadata (chunk_index, total_chunks, line_range).
AI agents call book_chunk to retrieve information from Self-hosted MCP server for Claude without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a straightforward read operation on pre-existing, locally-stored text file chunks. It has no side effects, does not modify or delete data, and does not execute code or trigger external operations. The blast radius of misuse is minimal—an agent could read sensitive local documents, but cannot alter them or cause irreversible harm. This is a standard Read category tool.
From the tool's definition Tool description explicitly states 'Read one chunk of a large text file' and 'Returns the chunk text plus metadata'. The purpose is retrieval of pre-split document content with no modification, creation, or deletion of data.
Attacks that exploit this kind of access
Read one chunk of a large text file (e.g. a book) that was pre-split into ~3000-word chunks by book_split. Use iteratively to read through a whole document that does not fit in the context window. Returns the chunk text plus metadata (chunk_index, total_chunks, line_range). It is categorised as a Read tool in the Self-hosted MCP server for Claude MCP Server, which means it retrieves data without modifying state.
Register the Self-hosted MCP server for Claude MCP server in PolicyLayer and add a rule for book_chunk: 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 Self-hosted MCP server for Claude. Nothing to install.
book_chunk 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 book_chunk 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 book_chunk. 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.
book_chunk is provided by the Self-hosted MCP server for Claude MCP server (leszczynskikarol/mcp-server). 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 →