task_manager · Anchor MCP: Risk & Policy

WHAT IT DOES

What task_manager does on Anchor

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

WHY IT NEEDS A POLICY

Why task_manager needs a policy

This tool modifies task records (creating/updating active tasks and marking tasks complete), which are reversible write operations. It does not execute arbitrary code, delete irreversibly, or handle financial operations. The 'get active task' and 'list all tasks' are read-only, but the tool's primary capability includes state modification.

From the tool's definition Tool description states it can 'set a new active task' and 'complete a task', which are write operations that modify persistent state. The server description emphasizes 'shared persistent working state' that persists across tools.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

task_manager Rate-limited

task_manager 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": {
    "task_manager": {
      "limits": [
        {
          "counter": "task_manager_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 Anchor, so you can run agents against it safely.

FAQ

Questions about task_manager

What does the task_manager tool do? +

Manage tasks: get active task, set a new active task, complete a task, or list all tasks. It is categorised as a Write tool in the Anchor MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on task_manager? +

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

What risk level is task_manager? +

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

Can I rate-limit task_manager? +

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

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

task_manager is provided by the Anchor MCP server (thewillmoss/anchor-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.