AI agents call list_streets to retrieve information from Mcp Dawa without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name 'list_streets' indicates retrieval of street data without modification. On a read-only address API service, this would retrieve or query street information with no side effects. Empty description lowers confidence slightly, but the name and server context strongly suggest a Read operation. Severity is low as it only retrieves public address data.
From the tool's definition Tool name 'list_streets' on an address API server (DAWA) that provides 'address search' and 'lookup' functionality. Description is empty, but context indicates a listing/retrieval operation.
Attacks that exploit this kind of access
list_streets. It is categorised as a Read tool in the Mcp Dawa MCP Server, which means it retrieves data without modifying state.
Register the Mcp Dawa MCP server in PolicyLayer and add a rule for list_streets: 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 Mcp Dawa. Nothing to install.
list_streets 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 list_streets 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 list_streets. 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.
list_streets is provided by the Mcp Dawa MCP server (itk-dev/mcp-dawa). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
list_streets is one line of Mcp Dawa's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →