get_ollama_version
AI agents call get_ollama_version 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 retrieves version metadata from Ollama, which is a read operation with no side effects. Version queries do not modify, execute, or delete anything. Even if misused by an AI agent, the worst outcome is unnecessary API calls or information disclosure of version numbers, which has minimal blast radius.
From the tool's definition Tool name 'get_ollama_version' indicates retrieval of version information. Sibling tools include 'get_version', 'get_api_doc_section', 'get_ollama_list', 'get_running_models', and 'list_models' which are all read-only retrieval operations.
Attacks that exploit this kind of access
get_ollama_version. 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_ollama_version: 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_ollama_version 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_ollama_version 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_ollama_version. 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_ollama_version 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 →