Check Ollama daemon connectivity and list currently running models.
AI agents call ollama_health to retrieve information from Ollama-Omega 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 and enumerates running models without creating, modifying, deleting, or executing anything. It is purely informational. Severity is low because the blast radius of misuse is minimal—an attacker could only learn about the Ollama daemon state and active models, which does not compromise system integrity or expose sensitive data beyond operational metadata.
From the tool's definition Tool name is 'ollama_health' and description states it 'Check[s] Ollama daemon connectivity and list[s] currently running models.' Both actions are read-only queries with no side effects.
Attacks that exploit this kind of access
Check Ollama daemon connectivity and list currently running models. It is categorised as a Read tool in the Ollama-Omega MCP Server, which means it retrieves data without modifying state.
Register the Ollama-Omega MCP server in PolicyLayer and add a rule for ollama_health: 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 Ollama-Omega. Nothing to install.
ollama_health 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 ollama_health 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 ollama_health. 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.
ollama_health is provided by the Ollama-Omega MCP server (vrtxomega/ollama-omega). 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 →