submit_work · AI Collaboration MCP Server MCP: Risk & Policy

WHAT IT DOES

What submit_work does on AI Collaboration MCP Server

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

WHY IT NEEDS A POLICY

Why submit_work needs a policy

An AI agent can call submit_work faster than any human can review — one bad instruction and it creates or modifies resources in AI Collaboration MCP Server by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

submit_work Rate-limited

submit_work 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": {
    "submit_work": {
      "limits": [
        {
          "counter": "submit_work_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 AI Collaboration MCP Server, so you can run agents against it safely.

FAQ

Questions about submit_work

What does the submit_work tool do? +

Submit completed work for review. It is categorised as a Write tool in the AI Collaboration MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on submit_work? +

Register the AI Collaboration MCP Server MCP server in PolicyLayer and add a rule for submit_work: 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 AI Collaboration MCP Server. Nothing to install.

What risk level is submit_work? +

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

Can I rate-limit submit_work? +

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

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

submit_work is provided by the AI Collaboration MCP Server MCP server (wyn0001/ai-collab-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.