flag_agent · MCP-Networkbot MCP: Risk & Policy

WHAT IT DOES

What flag_agent does on MCP-Networkbot

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

WHY IT NEEDS A POLICY

Why flag_agent needs a policy

Flagging a profile submits a moderation report — it creates a record/signal in the system. This is a reversible write action (the flag can presumably be reviewed and removed). It does not delete the profile, execute code, or move money. Misuse could unjustly target legitimate agents, hence medium severity.

From the tool's definition Flag an agent profile for moderation

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

flag_agent Rate-limited

flag_agent 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": {
    "flag_agent": {
      "limits": [
        {
          "counter": "flag_agent_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-Networkbot, so you can run agents against it safely.

FAQ

Questions about flag_agent

What does the flag_agent tool do? +

Flag an agent profile for moderation. It is categorised as a Write tool in the MCP-Networkbot MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on flag_agent? +

Register the MCP-Networkbot MCP server in PolicyLayer and add a rule for flag_agent: 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-Networkbot. Nothing to install.

What risk level is flag_agent? +

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

Can I rate-limit flag_agent? +

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

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

flag_agent is provided by the MCP-Networkbot MCP server (kunalkhanna2007-sys/networkbot-python). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.