Check Ollama health and whether a specific model is loaded in VRAM.
AI agents call model_status to retrieve information from OpenClaude MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves status information about Ollama health and model memory state. It performs monitoring/diagnostic checks without modifying, deleting, or executing external operations. The action is passive observation of system state, fitting the Read category definition of retrieving or querying data with no side effects.
From the tool's definition Tool name 'model_status' and description 'Check Ollama health and whether a specific model is loaded in VRAM' indicate read-only queries with no side effects.
Attacks that exploit this kind of access
Check Ollama health and whether a specific model is loaded in VRAM. It is categorised as a Read tool in the OpenClaude MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OpenClaude MCP Server MCP server in PolicyLayer and add a rule for model_status: 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 OpenClaude MCP Server. Nothing to install.
model_status 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 model_status 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 model_status. 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.
model_status is provided by the OpenClaude MCP Server MCP server (sandraschi/openclaude-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 →