AI agents call get_deps 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 performs a passive inspection of the notebook's cell dependency structure. It retrieves metadata about variable dependencies between cells but does not modify state, execute code, delete data, or trigger side effects. The operation is purely informational, consistent with other Read-category tools like 'get_cells', 'get_variables', and 'get_errors' on the same server.
From the tool's definition Tool name 'get_deps' and description 'Get the cell dependency graph showing which cells depend on which variables' indicate a read-only query operation that retrieves and displays dependency information without modifying or executing any code.
Attacks that exploit this kind of access
Get the cell dependency graph showing which cells depend on which variables. 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_deps: 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_deps 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_deps 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_deps. 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_deps 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 →