Break down a complex task into manageable subtasks
AI agents invoke decompose-task 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 invokes an Ollama LLM to process and decompose a task, which constitutes executing an external operation (LLM inference). While it does not directly modify data or delete anything, it runs a model computation whose effects depend on the input arguments.
From the tool's definition "Break down a complex task into manageable subtasks" — triggers an LLM inference operation via local Ollama instance to perform task decomposition
Documented attack patterns abuse exactly the kind of access decompose-task 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 decompose-task:
{
"version": "1",
"default": "deny",
"tools": {
"decompose-task": {
"limits": [
{
"counter": "decompose-task_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}decompose-task 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.
Break down a complex task into manageable subtasks. 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 decompose-task: 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.
decompose-task 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 decompose-task 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 decompose-task. 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.
decompose-task 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.