planning_search
AI agents call planning_search to retrieve information from UK Property Intelligence without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name contains 'search', which is a canonical Read operation (retrieves data without modification). The empty description is a confidence reducer, but the server's overall purpose (UK property intelligence wrapping public registries and data sources) and the pattern of sibling tools all pointing to lookup/retrieval functionality supports classifying this as a Read tool.
From the tool's definition Tool name 'planning_search' indicates a search/query operation. No description provided, but 'search' strongly suggests data retrieval rather than modification or execution.
Attacks that exploit this kind of access
planning_search. It is categorised as a Read tool in the UK Property Intelligence MCP Server, which means it retrieves data without modifying state.
Register the UK Property Intelligence MCP server in PolicyLayer and add a rule for planning_search: 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 UK Property Intelligence. Nothing to install.
planning_search 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 planning_search 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 planning_search. 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.
planning_search is provided by the UK Property Intelligence MCP server (paulieb89/uk-property-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 →