plan_manager · Anchor MCP: Risk & Policy

WHAT IT DOES

What plan_manager does on Anchor

AI agents use plan_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 plan_manager needs a policy

The tool performs both read and write operations on plan data. The write operations (save/update) are reversible and do not delete data, so it does not qualify as Destructive. It does not execute code or trigger external operations (Execute category), nor does it involve financial transactions.

From the tool's definition Tool description explicitly states 'save/update a plan', which are reversible write operations. Also includes 'read a plan' (Read category) and 'list all plan names' (Read category), but the most severe capability is write.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

plan_manager Rate-limited

plan_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": {
    "plan_manager": {
      "limits": [
        {
          "counter": "plan_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 plan_manager

What does the plan_manager tool do? +

Manage plans: read a plan, save/update a plan, or list all plan names. 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 plan_manager? +

Register the Anchor MCP server in PolicyLayer and add a rule for plan_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 plan_manager? +

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

Can I rate-limit plan_manager? +

Yes. Add a rate_limit block to the plan_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 plan_manager completely? +

Set action: deny in the PolicyLayer policy for plan_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 plan_manager? +

plan_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.