search_hansard
AI agents call search_hansard to retrieve information from GovUK MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Hansard searches retrieve historical parliamentary debate records—a read-only public data query with no side effects, data modification, or destructive capability. The empty description lowers confidence slightly, but context from sibling tools and server purpose strongly indicates this is a simple lookup operation. Low severity because the data is public and read-only access poses minimal risk.
From the tool's definition Tool name 'search_hansard' indicates querying Hansard (UK parliamentary records). The sibling tools on this server (find_courts, find_gp_surgeries, get_company, get_charity) are all read-only lookup/search operations.
Attacks that exploit this kind of access
search_hansard. It is categorised as a Read tool in the GovUK MCP Server MCP Server, which means it retrieves data without modifying state.
Register the GovUK MCP Server MCP server in PolicyLayer and add a rule for search_hansard: 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 GovUK MCP Server. Nothing to install.
search_hansard 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 search_hansard 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 search_hansard. 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.
search_hansard is provided by the GovUK MCP Server MCP server (stealth-labs-ltd/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 →