AI agents invoke chat_completion 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 executes a language model with arbitrary input prompts. While the LLM itself is not arbitrary code execution, chat completion APIs can be misused to generate harmful content, perform prompt injection attacks, or trigger unintended model behaviors with significant side effects. The blast radius depends on model capabilities and context length.
From the tool's definition Tool provides 'OpenAI-compatible chat completion API' which triggers execution of an LLM model with user-supplied prompts. The description indicates it 'run[s] AI models locally', making it code execution in nature.
Documented attack patterns abuse exactly the kind of access chat_completion 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 chat_completion:
{
"version": "1",
"default": "deny",
"tools": {
"chat_completion": {
"limits": [
{
"counter": "chat_completion_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}chat_completion 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.
OpenAI-compatible chat completion API. 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 chat_completion: 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.
chat_completion 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 chat_completion 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 chat_completion. 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.
chat_completion is provided by the Ollama MCP Server MCP server (nighttrek/ollama-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 10 Ollama MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
10 Ollama MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.