AI agents call detected_browsers to retrieve information from Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about installed browsers on the local system. It performs only data retrieval without modifying, executing, or deleting anything. The operation is read-only and has minimal security impact—browser enumeration alone cannot harm systems or data. Severity is low as this is reconnaissance-only information gathering.
From the tool's definition Tool name 'detected_browsers' and description 'List all browsers detected on this system' indicate a query/list operation with no side effects.
Attacks that exploit this kind of access
List all browsers detected on this system. It is categorised as a Read tool in the Memory MCP Server, which means it retrieves data without modifying state.
Register the Memory MCP server in PolicyLayer and add a rule for detected_browsers: 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 Memory. Nothing to install.
detected_browsers 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 detected_browsers 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 detected_browsers. 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.
detected_browsers is provided by the Memory MCP server (shaktisinhchavda/memory-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 →