complete_action · Exponential MCP: Risk & Policy

WHAT IT DOES

What complete_action does on Exponential MCP

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

WHY IT NEEDS A POLICY

Why complete_action needs a policy

This tool modifies data (marking an action's completion status) in a reversible manner—the action's completed status can presumably be toggled or updated back to incomplete. It does not delete data irreversibly (Destructive), execute arbitrary code (Execute), nor involve financial transactions (Financial). While it creates a side effect, it is a standard Write operation typical of project management tools.

From the tool's definition Tool name 'complete_action' and description 'Mark an action as completed' indicate a state-change operation on an action object within the Exponential workspace.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

complete_action Rate-limited

complete_action 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": {
    "complete_action": {
      "limits": [
        {
          "counter": "complete_action_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 Exponential MCP, so you can run agents against it safely.

FAQ

Questions about complete_action

What does the complete_action tool do? +

Mark an action as completed. It is categorised as a Write tool in the Exponential MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on complete_action? +

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

What risk level is complete_action? +

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

Can I rate-limit complete_action? +

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

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

complete_action is provided by the Exponential MCP server (positonic/exponential-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.