Rebuild text index. Useful for when contents have changed on disk
AI agents invoke rebuild to trigger actions in Library MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers a rebuild/reindex operation on disk contents. It's not a simple read, nor does it delete data, but it executes a potentially expensive indexing process that reads from disk and rewrites the search index. This falls under Execute as it triggers an external operation (index rebuild) whose effects depend on current disk state.
From the tool's definition Rebuild text index. Useful for when contents have changed on disk
Documented attack patterns abuse exactly the kind of access rebuild gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Library MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for rebuild:
{
"version": "1",
"default": "deny",
"tools": {
"rebuild": {
"limits": [
{
"counter": "rebuild_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}rebuild stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Rebuild text index. Useful for when contents have changed on disk. It is categorised as a Execute tool in the Library MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Library MCP server in PolicyLayer and add a rule for rebuild: 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 Library MCP. Nothing to install.
rebuild is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the rebuild 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 rebuild. 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.
rebuild is provided by the Library MCP server (lethain/library-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Library MCP, 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.
7 Library MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.