agent_update

THE RISK

Medium Risk

Why agent_update needs a policy

The tool writes progress information to a task record, which is a reversible operation. It does not execute code, delete data, move money, or trigger external side effects; it simply records progress metadata. The low severity reflects that misuse would only result in incorrect progress reporting without affecting task execution or data integrity.

From the tool's definition Tool description states 'Report progress on an agent task' — this is a status/progress update operation that modifies task state reversibly without destructive or executable effects.

Documented attack patterns abuse exactly the kind of access agent_update gives an agent:

POLICY

How to control agent_update

PolicyLayer is an MCP gateway — it sits between your AI agents and Conductor, and nothing reaches the server without passing your rules. This is the rule we recommend for agent_update:

policy.json

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

agent_update 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.

Create a free account and register Conductor — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Conductor tools

Write agent_cancelled Signal that agent work was cancelled in response to a cancel control message. Write agent_done Signal that all agent work is complete. Write archive_plan Archive a completed or abandoned plan, hiding it from default listings while preserving it Write create_plan Create a new plan and open it as the active context. Use this at the start of any goal tha Write create_task Create a new task. Pass parent_id to create a child of an existing task. Omit parent_id on Write open_plan Open an existing plan. Use this at the start of a session when resuming prior work. Openin Write plan_proposal Submit a structured plan proposal with a root task and child tasks. Write provision_tasks Create multiple tasks in a single call by providing a map of absolute task IDs to task spe

All 16 Conductor tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about agent_update

What does the agent_update tool do? +

Report progress on an agent task. Call this as you make progress. It is categorised as a Write tool in the Conductor MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on agent_update? +

Register the Conductor MCP server in PolicyLayer and add a rule for agent_update: 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 Conductor. Nothing to install.

What risk level is agent_update? +

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

Can I rate-limit agent_update? +

Yes. Add a rate_limit block to the agent_update 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 agent_update completely? +

Set action: deny in the PolicyLayer policy for agent_update. 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 agent_update? +

agent_update is provided by the Conductor MCP server (shannonbay/conductor). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Conductor tool call.

Start from Conductor, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →