AI agents use create_a2h_task to create or update resources in Jamot MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Jamot MCP environment.
Creating tasks modifies server state by adding new work items for human teams. While the description is empty, the name and context strongly suggest a Write operation. It is reversible (tasks can be deleted via 'delete_task'), so not Destructive.
From the tool's definition Tool name 'create_a2h_task' indicates task creation (a2h = agent-to-human). Sibling tools include 'delete_task' and 'edit_task', confirming this server manages task state. The server description mentions 'assign tasks' as a core function.
Attacks that exploit this kind of access
create_a2h_task. It is categorised as a Write tool in the Jamot MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Jamot MCP server in PolicyLayer and add a rule for create_a2h_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.
create_a2h_task is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_a2h_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 create_a2h_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.
create_a2h_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 →