semantic_index
Build the local vector index over enabled Apple apps for semantic search — replaces any existing index; embeddings need GEMINI_API_KEY or the Swift bridge.
This record as markdown: /tools/heznpc-airmcp/semantic-index.md
What semantic_index does on AirMCP
AI agents call semantic_index to permanently remove resources in AirMCP, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why semantic_index is rated Critical
The description explicitly states the operation 'replaces any existing index', meaning any prior index data is permanently overwritten without recovery. This is an irreversible destructive action on local index data. Severity is medium because it affects only a local derived artifact (the vector index) rather than primary user data, but misuse could disrupt semantic search functionality until a new index is built.
From the tool's definition 'replaces any existing index' — the tool overwrites/destroys the previously built vector index irreversibly when rebuilding it
Attacks that exploit this kind of access
The rule that runs semantic_index safely
PolicyLayer is an MCP gateway: it sits between your AI agents and AirMCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For semantic_index, this is the rule to start with:
semantic_index is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect AirMCP, apply this rule, and every semantic_index call is checked against it from then on.
Questions about semantic_index
Build the local vector index over enabled Apple apps for semantic search — replaces any existing index; embeddings need GEMINI_API_KEY or the Swift bridge. It is categorised as a Destructive tool in the AirMCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Air MCP server in PolicyLayer and add a rule for semantic_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 AirMCP. Nothing to install.
semantic_index is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the semantic_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 semantic_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.
semantic_index is provided by the Air MCP server (airmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Air, and thousands of servers like it.
Across the catalogue