AI agents call get_law to retrieve information from Egov Law without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only query against a legal database to fetch and display law information. It has no side effects, cannot modify the underlying data, and presents no risk of unintended consequences from misuse. The worst-case scenario would be retrieving sensitive but publicly available legal information, which poses minimal security risk.
From the tool's definition Tool retrieves law metadata and plain text preview from e-Gov Law Search. Verbs: 'Retrieve' indicates data retrieval with no modification. No mention of creating, modifying, deleting, executing, or financial operations.
Attacks that exploit this kind of access
Retrieve law metadata and a plain text preview from e-Gov Law Search. It is categorised as a Read tool in the Egov Law MCP Server, which means it retrieves data without modifying state.
Register the Egov Law MCP server in PolicyLayer and add a rule for get_law: 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 Egov Law. Nothing to install.
get_law 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 get_law 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 get_law. 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.
get_law is provided by the Egov Law MCP server (shayouworld/egov-law-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 →