Fetch AI-generated descriptions for locations using Brave Local Search API
AI agents call local_descriptions to retrieve information from Search MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves pre-generated location descriptions from the Brave Local Search API. 'Fetch' is a read operation that queries existing data without side effects. No mutations, deletions, code execution, or financial transactions are involved. This falls squarely under the Read category with low severity since it only retrieves publicly available search data.
From the tool's definition Tool name 'local_descriptions' with description 'Fetch AI-generated descriptions for locations' indicates retrieval of data.
Attacks that exploit this kind of access
Fetch AI-generated descriptions for locations using Brave Local Search API. It is categorised as a Read tool in the Search MCP MCP Server, which means it retrieves data without modifying state.
Register the Search MCP server in PolicyLayer and add a rule for local_descriptions: 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 MCP. Nothing to install.
local_descriptions 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 local_descriptions 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 local_descriptions. 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.
local_descriptions is provided by the Search MCP server (nanameru/websearch-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 →