Execute an Ollama model with the specified parameters
AI agents invoke run-model to trigger actions in Ollama MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers execution of a language model with user-supplied parameters. While not destructive or financial by itself, executing an LLM is a form of external code/operation invocation whose side effects (output generation, computational load, potential prompt injection exploits) depend on untrusted arguments.
From the tool's definition Tool description states 'Execute an Ollama model with the specified parameters' — the word 'Execute' indicates runtime invocation of external operations (the LLM model). The effects depend on model selection and input parameters, which could be arbitrary.
Documented attack patterns abuse exactly the kind of access run-model gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ollama MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for run-model:
{
"version": "1",
"default": "deny",
"tools": {
"run-model": {
"limits": [
{
"counter": "run-model_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run-model stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Execute an Ollama model with the specified parameters. It is categorised as a Execute tool in the Ollama MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Ollama MCP Server MCP server in PolicyLayer and add a rule for run-model: 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 Server. Nothing to install.
run-model is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the run-model 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 run-model. 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.
run-model is provided by the Ollama MCP Server MCP server (newaitees/ollama-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Ollama MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 Ollama MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.