mark_activity_done · Mcp Pipedrive MCP: Risk & Policy

WHAT IT DOES

What mark_activity_done does on Mcp Pipedrive

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

WHY IT NEEDS A POLICY

Why mark_activity_done needs a policy

The tool updates an activity's status/state, which is a write operation. It is not destructive because activities are not deleted and can be reopened (reversible). It is not executable code or financial. The medium severity reflects that status changes in a sales pipeline (Pipedrive) could impact business workflows, but the reversible nature and lack of data deletion limit the blast radius.

From the tool's definition Tool description states it marks an activity 'done (or reopen it)' with 'Auto-backed up' notation. This modifies the state/status of an existing activity record reversibly—activities can be reopened, making it a reversible state change rather than deletion.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mark_activity_done Rate-limited

mark_activity_done 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": {
    "mark_activity_done": {
      "limits": [
        {
          "counter": "mark_activity_done_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 Mcp Pipedrive, so you can run agents against it safely.

FAQ

Questions about mark_activity_done

What does the mark_activity_done tool do? +

Mark an activity done (or reopen it). Auto-backed up. It is categorised as a Write tool in the Mcp Pipedrive MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on mark_activity_done? +

Register the Mcp Pipedrive MCP server in PolicyLayer and add a rule for mark_activity_done: 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 Mcp Pipedrive. Nothing to install.

What risk level is mark_activity_done? +

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

Can I rate-limit mark_activity_done? +

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

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

mark_activity_done is provided by the Mcp Pipedrive MCP server (leonardoceron-yvy/yvy-mcp-pipedrive). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.