AI agents use book_save to create or update resources in Legado — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Legado environment.
The tool name 'book_save' most likely creates or modifies book records in the Legado system. Without a description, we infer from context that it writes/persists book data rather than reading it. This is reversible (books can be edited or deleted), so it is Write rather than Destructive.
From the tool's definition Tool name 'book_save' combined with server context showing tools for managing book data (book_add_local, book_delete, book_save_progress, book_search). The 'save' operation implies modifying or persisting book state.
Documented attack patterns abuse exactly the kind of access book_save gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Legado, and nothing reaches the server without passing your rules. This is the rule we recommend for book_save:
{
"version": "1",
"default": "deny",
"tools": {
"book_save": {
"limits": [
{
"counter": "book_save_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}book_save stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
book_save. It is categorised as a Write tool in the Legado MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Legado MCP server in PolicyLayer and add a rule for book_save: 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 Legado. Nothing to install.
book_save is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the book_save 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_save. 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_save is provided by the Legado MCP server (joestar817/legado-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Legado, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
31 Legado tools catalogued and risk-classified — across an index of 43,000+ MCP servers.