Build or rebuild the Whoosh search index from documentation files.
AI agents use build_documentation_index to create or update resources in Whoosh RAG MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Whoosh RAG MCP environment.
This tool creates or overwrites a search index from existing documentation files. It is a Write operation (constructing/reconstructing index data), not Destructive since the source documentation files themselves are not deleted. However, rebuilding the index does overwrite any existing index, which could cause temporary unavailability or loss of prior index customizations.
From the tool's definition 'Build or rebuild the Whoosh search index from documentation files'
Attacks that exploit this kind of access
Build or rebuild the Whoosh search index from documentation files. It is categorised as a Write tool in the Whoosh RAG MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Whoosh RAG MCP server in PolicyLayer and add a rule for build_documentation_index: 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 Whoosh RAG MCP. Nothing to install.
build_documentation_index 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 build_documentation_index 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 build_documentation_index. 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.
build_documentation_index is provided by the Whoosh RAG MCP server (jianlins/whoosh_rag_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 →