Extract actual Python/SQL code from recipes
AI agents call get_recipe_code to retrieve information from Dataiku DSS MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns code that already exists in recipes without executing it, modifying it, or causing side effects. It is a data retrieval operation analogous to viewing source code in a repository. The low severity reflects minimal blast radius—exposing recipe code could reveal business logic but does not itself execute operations, modify data, or trigger external actions.
From the tool's definition Tool name 'get_recipe_code' and description 'Extract actual Python/SQL code from recipes' indicate retrieval of existing code without modification or execution. The verb 'extract' denotes a read-only operation.
Attacks that exploit this kind of access
Extract actual Python/SQL code from recipes. It is categorised as a Read tool in the Dataiku DSS MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Dataiku DSS MCP Server MCP server in PolicyLayer and add a rule for get_recipe_code: 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 Dataiku DSS MCP Server. Nothing to install.
get_recipe_code 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_recipe_code 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_recipe_code. 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_recipe_code is provided by the Dataiku DSS MCP Server MCP server (steven0lisa/mcp-dataiku). 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 →