AI agents call get_recent_history to retrieve information from Search History MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical browsing data without modifying or deleting it. While browser history can contain sensitive personal information (raising privacy concerns), the classification here concerns functional risk: the tool performs a Read operation. Severity is low because retrieval alone does not cause direct harm—the risk is informational exposure rather than operational damage.
From the tool's definition Tool name 'get_recent_history' and server description indicate retrieval of browser history data with 'no side effects' - the server enables 'access to and searching of browser history' and 'retrieve past browsing data'.
Documented attack patterns abuse exactly the kind of access get_recent_history gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Search History MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_recent_history:
{
"version": "1",
"default": "deny",
"tools": {
"get_recent_history": {}
}
}get_recent_history is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
get_recent_history. It is categorised as a Read tool in the Search History MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Search History MCP Server MCP server in PolicyLayer and add a rule for get_recent_history: 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 Search History MCP Server. Nothing to install.
get_recent_history 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 get_recent_history 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 get_recent_history. 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.
get_recent_history is provided by the Search History MCP Server MCP server (ronantakizawa/search-history-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Search History MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
3 Search History MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.