compute_correlation
AI agents call compute_correlation to retrieve information from MCP Tabular Data Analysis Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Correlation computation is a statistical read operation that queries and analyzes data without modifying, deleting, or executing external code. The empty description reduces confidence slightly, but the context from server purpose and sibling tools strongly indicates this is an analytical read-only function. No data is written, deleted, or financial operations are involved.
From the tool's definition Tool name 'compute_correlation' and server description indicating 'analysis of CSV files and SQLite databases through tools for statistics, correlations' suggests a query/analysis operation.
Attacks that exploit this kind of access
compute_correlation. It is categorised as a Read tool in the MCP Tabular Data Analysis Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Tabular Data Analysis Server MCP server in PolicyLayer and add a rule for compute_correlation: 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 MCP Tabular Data Analysis Server. Nothing to install.
compute_correlation 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 compute_correlation 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 compute_correlation. 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.
compute_correlation is provided by the MCP Tabular Data Analysis Server MCP server (k02d/mcp-tabular). 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 →