get_running_models
AI agents call get_running_models to retrieve information from Ollama_MCP_Guidance without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries state information about running models without creating, modifying, deleting, or executing external operations. It is a passive information retrieval operation typical of diagnostic or monitoring queries against the Ollama service. The blast radius of misuse is minimal—returning incorrect or stale model lists would not harm data or systems.
From the tool's definition Tool name 'get_running_models' indicates a read operation that retrieves the list of currently active models from Ollama. Sibling tools like 'list_models' and 'get_ollama_list' follow similar informational patterns.
Attacks that exploit this kind of access
get_running_models. It is categorised as a Read tool in the Ollama_MCP_Guidance MCP Server, which means it retrieves data without modifying state.
Register the Ollama_MCP_Guidance MCP server in PolicyLayer and add a rule for get_running_models: 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_MCP_Guidance. Nothing to install.
get_running_models 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_running_models 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_running_models. 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_running_models is provided by the Ollama_MCP_Guidance MCP server (shadovvsinger/ollama_mcp_guidance). 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 →