AI agents invoke decompose_task to trigger actions in Jamot MCP. 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.
The tool name suggests it breaks down complex tasks into subtasks, which likely involves creating multiple new task records (Write/Execute behavior). However, the description is empty, so the exact behavior is unknown. Based on the server context about decomposing complex instructions and coordinating human teams, this likely triggers automated task creation or orchestration logic.
From the tool's definition Tool name 'decompose_task' and server description mentions 'decompose complex instructions' as a key capability
Attacks that exploit this kind of access
decompose_task. It is categorised as a Execute tool in the Jamot MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Jamot 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 Jamot MCP. 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 Jamot MCP server (jamot-pro/jamot-mcp). 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 →