AI agents call get_variable to retrieve information from MATLAB MCP Tool without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name 'get_variable' and its placement among other get/retrieve operations indicates it queries and returns MATLAB workspace variable data without modifying, deleting, or executing anything. While the description is empty, the clear naming and context from sibling tools provide strong evidence of read-only behavior.
From the tool's definition Tool name is 'get_variable' which retrieves workspace variables. Sibling tools include 'get_figure_metadata', 'get_plot_data', 'get_analysis_prompt' which are all Read operations.
Documented attack patterns abuse exactly the kind of access get_variable gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MATLAB MCP Tool, and nothing reaches the server without passing your rules. This is the rule we recommend for get_variable:
{
"version": "1",
"default": "deny",
"tools": {
"get_variable": {}
}
} get_variable is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
get_variable. It is categorised as a Read tool in the MATLAB MCP Tool MCP Server, which means it retrieves data without modifying state.
Register the MATLAB MCP Tool MCP server in PolicyLayer and add a rule for get_variable: 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 MATLAB MCP Tool. Nothing to install.
get_variable 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_variable 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_variable. 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_variable is provided by the MATLAB MCP Tool MCP server (neuromechanist/matlab-mcp-tools). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MATLAB MCP Tool, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
15 MATLAB MCP Tool tools catalogued and risk-classified — across an index of 43,000+ MCP servers.