AI agents call profile_data 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 performs statistical analysis and profiling of data, which is fundamentally a read operation. It queries data to compute descriptive statistics (null rates, quartiles, min/max values) but does not create, modify, delete, or execute arbitrary code. There are no side effects or data mutations. The operation is safe for an AI agent to call as it cannot cause data loss or unintended state changes.
From the tool's definition Tool description states it 'Run[s] a deep data profile on a table' returning 'stats: null rate, distinct count, min/max/avg, quartiles'.
Attacks that exploit this kind of access
Run a deep data profile on a table using DuckDB SUMMARIZE. Returns stats: null rate, distinct count, min/max/avg, quartiles. 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 profile_data: 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.
profile_data 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 profile_data 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 profile_data. 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.
profile_data 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 →