get_kedro_context · Kedro RAG MCP: Risk & Policy

WHAT IT DOES

What get_kedro_context does on Kedro RAG MCP

AI agents call get_kedro_context to retrieve information from Kedro RAG MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

WHY IT NEEDS A POLICY

Why get_kedro_context needs a policy

The tool name 'get_' prefix indicates a retrieval operation. Without a description, confidence is moderate, but the server's read-only query-focused design and pattern of sibling search/stats tools suggest this retrieves information rather than modifying state. No code execution, deletion, or financial operations are implied.

From the tool's definition Tool name 'get_kedro_context' with no description provided. Based on the server's purpose (querying Kedro framework documentation) and sibling tools (search_kedro_docs, kedro_knowledge_stats, rebuild_kedro_knowledge), this appears to be a data retrieval…

Attacks that exploit this kind of access

Questions about get_kedro_context

What does the get_kedro_context tool do? +

get_kedro_context. It is categorised as a Read tool in the Kedro RAG MCP MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_kedro_context? +

Register the Kedro RAG MCP server in PolicyLayer and add a rule for get_kedro_context: 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 Kedro RAG MCP. Nothing to install.

What risk level is get_kedro_context? +

get_kedro_context is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get_kedro_context? +

Yes. Add a rate_limit block to the get_kedro_context 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.

How do I block get_kedro_context completely? +

Set action: deny in the PolicyLayer policy for get_kedro_context. 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.

What MCP server provides get_kedro_context? +

get_kedro_context is provided by the Kedro RAG MCP server (sajidalamqb/kedro-mcp-rag). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.