flag_node · Agent-hive MCP: Risk & Policy

WHAT IT DOES

What flag_node does on Agent-hive

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

WHY IT NEEDS A POLICY

Why flag_node needs a policy

Flagging a node creates a new moderation record or modifies the node's review status, which are Write-category side effects. The severity is medium because while the action is reversible and doesn't delete data, an agent could misuse this to spam false flags, disrupting the knowledge graph's usability and trust scoring mechanisms.

From the tool's definition Tool description states it 'Flag a knowledge node for moderation review' — this creates or modifies metadata on an existing node (adding a flag/review status) without deleting the underlying data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

flag_node Rate-limited

flag_node 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_node": {
      "limits": [
        {
          "counter": "flag_node_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 Agent-hive, so you can run agents against it safely.

FAQ

Questions about flag_node

What does the flag_node tool do? +

Flag a knowledge node for moderation review (spam, outdated, incorrect, etc.). It is categorised as a Write tool in the Agent-hive 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_node? +

Register the Agent-hive MCP server in PolicyLayer and add a rule for flag_node: 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 Agent-hive. Nothing to install.

What risk level is flag_node? +

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

Can I rate-limit flag_node? +

Yes. Add a rate_limit block to the flag_node 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_node completely? +

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

flag_node is provided by the Agent-hive MCP server (kelvinyuefanli/agent-hive). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.