mark_processed · Teammate MCP: Risk & Policy

WHAT IT DOES

What mark_processed does on Teammate

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

WHY IT NEEDS A POLICY

Why mark_processed needs a policy

The name 'mark_processed' indicates marking a message or queue item as processed—a reversible state change typical of Write operations. Without a description, confidence is moderate. Severity is medium because marking items as processed in a queue could cause messages to be skipped or lost if misused, but the operation itself is typically reversible depending on system design.

From the tool's definition Tool name 'mark_processed' suggests state modification. Description is empty, limiting certainty. Context shows this is part of a messaging/queue system (see 'inbox' and 'queue_status' sibling tools).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mark_processed Rate-limited

mark_processed 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_processed": {
      "limits": [
        {
          "counter": "mark_processed_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 Teammate, so you can run agents against it safely.

FAQ

Questions about mark_processed

What does the mark_processed tool do? +

mark_processed. It is categorised as a Write tool in the Teammate 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_processed? +

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

What risk level is mark_processed? +

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

Can I rate-limit mark_processed? +

Yes. Add a rate_limit block to the mark_processed 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_processed completely? +

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

mark_processed is provided by the Teammate MCP server (jonghklee/teammate-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.