LITERAL substring search across main-tree TAB nodes ONLY (groups, windows, folders, libraries, bookmarks, and notes are NOT searched here). Matches title, URL, memo text, and tags. Kept for backward compatibility — for broader literal search across non-tab nodes, libraries, bookmarks, and notes c...
AI agents call search_tabs to retrieve information from Pinako AI Bridge without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
search_tabs queries and retrieves tab data based on search criteria. It is explicitly a read-only operation that searches existing data without creating, modifying, deleting, or executing any actions. The low severity reflects minimal blast radius if misused — an AI agent searching tabs cannot harm the system or data.
From the tool's definition Tool performs 'substring search across main-tree TAB nodes ONLY' and 'Matches title, URL, memo text, and tags' — purely a retrieval operation with no side effects or data modification.
Attacks that exploit this kind of access
LITERAL substring search across main-tree TAB nodes ONLY (groups, windows, folders, libraries, bookmarks, and notes are NOT searched here). Matches title, URL, memo text, and tags. Kept for backward compatibility — for broader literal search across non-tab nodes, libraries, bookmarks, and notes content, USE search_pinako instead (it is the omnibus version with a scope parameter). Use ONLY when the user names a literal substring (. It is categorised as a Read tool in the Pinako AI Bridge MCP Server, which means it retrieves data without modifying state.
Register the Pinako AI Bridge MCP server in PolicyLayer and add a rule for 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 Pinako AI Bridge. Nothing to install.
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 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 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.
search_tabs is provided by the Pinako AI Bridge MCP server (teleomorph/pinako-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 →