safari_search_tabs
Searches the rendered text of every open Safari tab for a substring. Returns each matching tab with the surrounding snippet. Useful for 'do I have a tab open with X?' questions across dozens of tabs.
This record as markdown: /tools/com-local-mcp-local-mcp/safari-search-tabs.md
What safari_search_tabs does on Local
AI agents call safari_search_tabs to retrieve information from Local without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
query | string | Yes | Substring to search for (case-insensitive) |
context | integer | — | Characters of context around each match (default 120) |
max_tabs | integer | — | Max tabs to scan (default 30). Higher = slower. |
Parameters from the server's own tool schema.
Why safari_search_tabs is rated Low
The tool retrieves and queries data from open browser tabs without executing code, modifying content, or causing side effects. It is a passive search utility that helps answer questions about what tabs are open, fitting squarely into the Read category. Severity is low because the blast radius of misuse is limited to information disclosure of tab titles and visible text the user is already viewing.
From the tool's definition Tool 'searches the rendered text of every open Safari tab for a substring' and 'returns each matching tab with the surrounding snippet' — purely read-only operations that query browser state without modification.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs safari_search_tabs safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Local, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For safari_search_tabs, this is the rule to start with:
safari_search_tabs is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Local, apply this rule, and every safari_search_tabs call is checked against it from then on.
Questions about safari_search_tabs
Searches the rendered text of every open Safari tab for a substring. Returns each matching tab with the surrounding snippet. Useful for 'do I have a tab open with X?' questions across dozens of tabs. It is categorised as a Read tool in the Local MCP Server, which means it retrieves data without modifying state.
safari_search_tabs accepts 3 parameters: query, context, max_tabs. Required: query. The full parameter table on this page comes from the server's own tool schema.
Register the Local MCP server in PolicyLayer and add a rule for safari_search_tabs: 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 Local. Nothing to install.
safari_search_tabs 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 safari_search_tabs 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 safari_search_tabs. 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.
safari_search_tabs is provided by the Local MCP server (local-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Local, and thousands of servers like it.
This server
Across the catalogue