oboe_mark_complete · Obo MCP: Risk & Policy

WHAT IT DOES

What oboe_mark_complete does on Obo

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

WHY IT NEEDS A POLICY

Why oboe_mark_complete needs a policy

This tool creates or modifies data (marks items/sessions as complete) in a reversible manner. It does not delete data (would be Destructive), execute arbitrary code (would be Execute), or move money (would be Financial). The empty description lowers confidence slightly, but the name and sibling tool patterns strongly indicate a Write operation that updates workflow state.

From the tool's definition Tool name 'oboe_mark_complete' indicates state modification of session/item objects. Server context describes 'managing One-By-One review sessions' with 'item management within standardized JSON workflows.' The 'mark_complete' action modifies item or session…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

oboe_mark_complete Rate-limited

oboe_mark_complete 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": {
    "oboe_mark_complete": {
      "limits": [
        {
          "counter": "oboe_mark_complete_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 Obo, so you can run agents against it safely.

FAQ

Questions about oboe_mark_complete

What does the oboe_mark_complete tool do? +

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

How do I enforce a policy on oboe_mark_complete? +

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

What risk level is oboe_mark_complete? +

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

Can I rate-limit oboe_mark_complete? +

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

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

oboe_mark_complete is provided by the Obo MCP server (warnes-innovations/oboe-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.