AI agents call get_variables to retrieve information from Marimo 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 the current state of variables and data tables within a notebook environment. It performs a read-only operation that does not modify, execute, or delete any data. While it may expose sensitive information if variables contain secrets or PII, the blast radius of misuse is limited to information disclosure rather than data loss, code execution, or financial impact.
From the tool's definition Tool name 'get_variables' and description 'Get all variable values and data tables in the notebook' indicate retrieval of state with no side effects.
Attacks that exploit this kind of access
Get all variable values and data tables in the notebook. It is categorised as a Read tool in the Marimo MCP Server, which means it retrieves data without modifying state.
Register the Marimo MCP server in PolicyLayer and add a rule for get_variables: 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 Marimo. Nothing to install.
get_variables 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_variables 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_variables. 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_variables is provided by the Marimo MCP server (vladisluv12/marimo-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 →