plan · Context MCP: Risk & Policy

WHAT IT DOES

What plan does on Context

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

WHY IT NEEDS A POLICY

Why plan needs a policy

The 'plan' tool creates or modifies data by saving planning information to persistent storage (project store) and potentially writing files to disk. This is a Write operation—it persists new or updated content without deleting existing data and is reversible.

From the tool's definition Tool description states it 'saves to project store, optionally writes a .md file to planDir', indicating data creation/modification operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

plan Rate-limited

plan 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": {
      "limits": [
        {
          "counter": "plan_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 Context, so you can run agents against it safely.

FAQ

Questions about plan

What does the plan tool do? +

Plan storage — saves to project store, optionally writes a .md file to planDir.\n. It is categorised as a Write tool in the Context 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? +

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

What risk level is plan? +

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

Can I rate-limit plan? +

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

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

plan is provided by the Context MCP server (vibhasdutta/context-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.