add_task_to_pipeline · Agent-Comm-Hub MCP: Risk & Policy

WHAT IT DOES

What add_task_to_pipeline does on Agent-Comm-Hub

AI agents use add_task_to_pipeline to create or update resources in Agent-Comm-Hub — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Agent-Comm-Hub environment.

WHY IT NEEDS A POLICY

Why add_task_to_pipeline needs a policy

This tool creates new task entries and modifies pipeline structure. While it affects execution flow and potentially triggers downstream operations, the core capability is data creation/insertion (Write category). It is not Destructive (not irreversible deletion), not Financial, and not Execute (does not run arbitrary code—it enqueues tasks for others to execute).

From the tool's definition Tool adds/creates tasks to a pipeline ('将任务添加到 Pipeline' = 'Add task to Pipeline'). The description indicates it modifies pipeline state by inserting tasks at specified positions ('指定任务在 Pipeline 中的顺序' = 'specify task order in Pipeline').

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_task_to_pipeline Rate-limited

add_task_to_pipeline stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "add_task_to_pipeline": {
      "limits": [
        {
          "counter": "add_task_to_pipeline_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Agent-Comm-Hub, so you can run agents against it safely.

FAQ

Questions about add_task_to_pipeline

What does the add_task_to_pipeline tool do? +

将任务添加到 Pipeline。指定任务在 Pipeline 中的顺序。不传 order_index 则自动追加到末尾。. It is categorised as a Write tool in the Agent-Comm-Hub MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_task_to_pipeline? +

Register the Agent-Comm-Hub MCP server in PolicyLayer and add a rule for add_task_to_pipeline: 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 Agent-Comm-Hub. Nothing to install.

What risk level is add_task_to_pipeline? +

add_task_to_pipeline is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit add_task_to_pipeline? +

Yes. Add a rate_limit block to the add_task_to_pipeline 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.

How do I block add_task_to_pipeline completely? +

Set action: deny in the PolicyLayer policy for add_task_to_pipeline. 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.

What MCP server provides add_task_to_pipeline? +

add_task_to_pipeline is provided by the Agent-Comm-Hub MCP server (liuboacean/agent-comm-hub). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.