check_ollama

Check Ollama LLM server health via GET /api/version. Returns version string. Default port 11434.

SERVERMcp Nettools SOURCEaaronckj/mcp-nettools

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/aaronckj-mcp-nettools/check-ollama.md

WHAT IT DOES

What check_ollama does on Mcp Nettools

AI agents call check_ollama to retrieve information from Mcp Nettools without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why check_ollama is rated Low

This is a read-only diagnostic operation that retrieves health/version information from a service. It has no side effects on the target system, no code execution capability, and no data modification or deletion. The GET /api/version endpoint is a standard health check pattern with minimal blast radius if called by an AI agent.

From the tool's definition Tool performs a GET request to retrieve version information from an Ollama server. Description explicitly states 'Returns version string' with no mention of modifications, deletions, or external operations beyond querying a status endpoint.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs check_ollama safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Mcp Nettools, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For check_ollama, this is the rule to start with:

check_ollama Allowed

check_ollama is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "check_ollama": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Mcp Nettools, apply this rule, and every check_ollama call is checked against it from then on.

FAQ

Questions about check_ollama

What does the check_ollama tool do? +

Check Ollama LLM server health via GET /api/version. Returns version string. Default port 11434. It is categorised as a Read tool in the Mcp Nettools MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on check_ollama? +

Register the Mcp Nettools MCP server in PolicyLayer and add a rule for check_ollama: 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 Mcp Nettools. Nothing to install.

What risk level is check_ollama? +

check_ollama is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit check_ollama? +

Yes. Add a rate_limit block to the check_ollama 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.

How do I block check_ollama completely? +

Set action: deny in the PolicyLayer policy for check_ollama. 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.

What MCP server provides check_ollama? +

check_ollama is provided by the Mcp Nettools MCP server (aaronckj/mcp-nettools). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Mcp Nettools, and thousands of servers like it.

This server

All 235 Mcp Nettools tools →

Across the catalogue

The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →