AI agents call list_legal_sources to retrieve information from Legal without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a query tool that retrieves metadata about available legal resources. It performs a read-only operation (listing) with no side effects. There is no code execution, data modification, deletion, or financial impact. The low severity reflects the minimal blast radius—even if an agent abuses this tool, it can only discover what legal sources are available, with no consequential harm.
From the tool's definition Tool name 'list_legal_sources' and description 'List available legal corpora' indicate a retrieval/enumeration operation with no modification, deletion, or execution.
Attacks that exploit this kind of access
List available legal corpora. It is categorised as a Read tool in the Legal MCP Server, which means it retrieves data without modifying state.
Register the Legal MCP server in PolicyLayer and add a rule for list_legal_sources: 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 Legal. Nothing to install.
list_legal_sources 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 list_legal_sources 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 list_legal_sources. 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.
list_legal_sources is provided by the Legal MCP server (mcpservings/legal-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 →