govuk_grep_content
AI agents call govuk_grep_content 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.
The tool appears designed to search or filter content from GOV.UK based on the 'grep' naming convention and server context. Grep is a standard search utility. With no side effects indicated and aligned with the server's read-only retrieval capabilities, this is classified as Read.
From the tool's definition Tool name contains 'grep' (search/filter operation) and 'content', combined with server description stating 'search, content retrieval' capabilities. No description provided for the specific tool.
Attacks that exploit this kind of access
govuk_grep_content. 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_grep_content: 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_grep_content 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_grep_content 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_grep_content. 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_grep_content 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 →