AI agents call get_join_paths to retrieve information from Lucid without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about table relationships (foreign keys and column mappings) to inform query construction. It performs introspection only, returning information about how tables can be joined without executing queries, modifying data, or triggering external operations.
From the tool's definition Tool name is 'get_join_paths' and description states it 'Discover JOIN paths between two tables' and 'Returns direct paths'. The verb 'discover' and 'returns' indicate data retrieval/querying with no modification or execution of operations.
Attacks that exploit this kind of access
Discover JOIN paths between two tables. Returns direct paths (FK, column name. It is categorised as a Read tool in the Lucid MCP Server, which means it retrieves data without modifying state.
Register the Lucid MCP server in PolicyLayer and add a rule for get_join_paths: 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 Lucid. Nothing to install.
get_join_paths 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_join_paths 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_join_paths. 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_join_paths is provided by the Lucid MCP server (wiseriaai/lucid-skill). 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 →