read_vmrs
AI agents call read_vmrs to retrieve information from ModelRisk MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'read_' prefix strongly indicates a retrieval operation with no side effects. Without a description, confidence is moderate, but the naming convention and context of sibling tools (all read/query operations like get_cell, get_simulation_results) support classification as Read. No destructive, financial, or code execution capability is apparent from the name alone.
From the tool's definition Tool name 'read_vmrs' uses the 'read' prefix, suggesting it retrieves data. No description provided, but in the context of ModelRisk MCP (Monte Carlo risk modeling), 'VMRS' likely refers to a data structure or report that the tool queries.
Attacks that exploit this kind of access
read_vmrs. It is categorised as a Read tool in the ModelRisk MCP MCP Server, which means it retrieves data without modifying state.
Register the ModelRisk MCP server in PolicyLayer and add a rule for read_vmrs: 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 ModelRisk MCP. Nothing to install.
read_vmrs 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 read_vmrs 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 read_vmrs. 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.
read_vmrs is provided by the ModelRisk MCP server (vosesoftware/modelrisk-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 →