AI agents call bing_list_sites to retrieve information from Geoseo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and enumerates existing data (verified sites) belonging to the API key owner. This is a straightforward read operation that returns information without creating, modifying, deleting, or executing any external actions. The blast radius is minimal since it only exposes metadata already associated with the authenticated user's account.
From the tool's definition Tool name is 'bing_list_sites' and description states 'List all Bing-verified sites for the API key owner' — purely a retrieval/query operation with no modification or side effects.
Attacks that exploit this kind of access
List all Bing-verified sites for the API key owner. It is categorised as a Read tool in the Geoseo MCP Server, which means it retrieves data without modifying state.
Register the Geoseo MCP server in PolicyLayer and add a rule for bing_list_sites: 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 Geoseo. Nothing to install.
bing_list_sites 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 bing_list_sites 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 bing_list_sites. 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.
bing_list_sites is provided by the Geoseo MCP server (rachit8484/geoseo-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 →