govuk_search
AI agents call govuk_search to retrieve information from GOV UK Search without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs search operations on public GOV.UK data. Search is a retrieval function with no side effects—it queries existing data without creating, modifying, deleting, or executing code. The broader context confirms the server is for read-only access to government information. Severity is low because misuse cannot damage systems or data; worst case is information disclosure of already-public content.
From the tool's definition Tool name 'govuk_search' and server purpose describe 'search, content retrieval' functionality; description field is empty but sibling tools (govuk_get_content, govuk_get_organisation, govuk_grep_content, govuk_list_organisations, govuk_lookup_postcode) all…
Attacks that exploit this kind of access
govuk_search. It is categorised as a Read tool in the GOV UK Search MCP Server, which means it retrieves data without modifying state.
Register the GOV UK Search MCP server in PolicyLayer and add a rule for govuk_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 GOV UK Search. Nothing to install.
govuk_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 govuk_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 govuk_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.
govuk_search is provided by the GOV UK Search MCP server (paulieb89/govuk-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 →