Load bookmarks and history data from files
AI agents call load_bookmark_data to retrieve information from Tavily Web Search MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and loads bookmark and history data from local storage. It performs a retrieval operation with no side effects (no creation, modification, or deletion of data). While it accesses potentially sensitive personal data (browsing history, bookmarks), the action itself is non-destructive and corresponds to a Read category.
From the tool's definition Tool name and description indicate data retrieval: "Load bookmarks and history data from files" – a read operation that retrieves existing data without modification.
Attacks that exploit this kind of access
Load bookmarks and history data from files. It is categorised as a Read tool in the Tavily Web Search MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Tavily Web Search MCP Server MCP server in PolicyLayer and add a rule for load_bookmark_data: 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 Tavily Web Search MCP Server. Nothing to install.
load_bookmark_data 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 load_bookmark_data 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 load_bookmark_data. 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.
load_bookmark_data is provided by the Tavily Web Search MCP Server MCP server (upendranath/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 →