Get uncategorized URLs for custom categorization. Use this after running analysis.
AI agents call suggest_categories to retrieve information from Browser History Analysis MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only operation that queries and returns uncategorized URLs from the browser history database. There are no side effects, data modifications, deletions, code execution, or financial implications. The user is reviewing data to prepare for manual categorization, but the tool itself only retrieves existing information.
From the tool's definition The tool is described as 'Get uncategorized URLs for custom categorization,' which retrieves and returns data from the browser history analysis without modifying, deleting, or executing any operations.
Documented attack patterns abuse exactly the kind of access suggest_categories gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Browser History Analysis MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for suggest_categories:
{
"version": "1",
"default": "deny",
"tools": {
"suggest_categories": {}
}
}suggest_categories 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 uncategorized URLs for custom categorization. Use this after running analysis. It is categorised as a Read tool in the Browser History Analysis MCP MCP Server, which means it retrieves data without modifying state.
Register the Browser History Analysis MCP server in PolicyLayer and add a rule for suggest_categories: 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 Browser History Analysis MCP. Nothing to install.
suggest_categories 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 suggest_categories 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 suggest_categories. 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.
suggest_categories is provided by the Browser History Analysis MCP server (mixophrygian/browser_history_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Browser History Analysis MCP, 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.
7 Browser History Analysis MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.