AI agents call gsd_websearch to retrieve information from Gsd without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information from the web via an external search API. It has no side effects, does not modify data, does not execute arbitrary code, and does not involve financial transactions. It is a straightforward read operation that retrieves public search results.
From the tool's definition Tool name is 'gsd_websearch' and description states it 'Search[es] the web via Brave API'. Search operations are read-only queries that retrieve information without modifying or executing operations on the user's systems or data.
Attacks that exploit this kind of access
Search the web via Brave API (requires GSD Brave config). It is categorised as a Read tool in the Gsd MCP Server, which means it retrieves data without modifying state.
Register the Gsd MCP server in PolicyLayer and add a rule for gsd_websearch: 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 Gsd. Nothing to install.
gsd_websearch 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 gsd_websearch 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 gsd_websearch. 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.
gsd_websearch is provided by the Gsd MCP server (m0-ar/gsd-mcp-server). 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 →