Return project migration instructions.
AI agents call project_migration to retrieve information from Kedro MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves versioned guidance/instructions for migrating Kedro projects. It performs no side effects, creates no resources, executes no code, and deletes nothing. The action is purely informational (Read category). Severity is low because even if misused, the worst outcome is returning incorrect migration guidance, which does not damage systems or data.
From the tool's definition Tool returns 'project migration instructions' — a read operation that retrieves guidance documentation without modifying, executing, or deleting any data.
Attacks that exploit this kind of access
Return project migration instructions. It is categorised as a Read tool in the Kedro MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Kedro MCP Server MCP server in PolicyLayer and add a rule for project_migration: 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 MCP Server. Nothing to install.
project_migration 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 project_migration 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 project_migration. 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.
project_migration is provided by the Kedro MCP Server MCP server (kedro-org/kedro-mcp). 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 →