submit_proof · Agent-hive MCP: Risk & Policy

WHAT IT DOES

What submit_proof does on Agent-hive

AI agents use submit_proof 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 submit_proof needs a policy

submit_proof creates or records new execution proofs linked to knowledge nodes. This is a data modification operation (Write category) rather than Read (no retrieval), Execute (no arbitrary code execution or external triggers), Destructive (reversible), or Financial.

From the tool's definition Tool name 'submit_proof' and description 'Submit an execution proof for a knowledge node, proving it works in a specific environment' indicate creation or modification of proof/evidence data associated with nodes in the knowledge graph.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

submit_proof Rate-limited

submit_proof 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_proof": {
      "limits": [
        {
          "counter": "submit_proof_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 submit_proof

What does the submit_proof tool do? +

Submit an execution proof for a knowledge node, proving it works in a specific environment. 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 submit_proof? +

Register the Agent-hive MCP server in PolicyLayer and add a rule for submit_proof: 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 submit_proof? +

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

Can I rate-limit submit_proof? +

Yes. Add a rate_limit block to the submit_proof 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_proof completely? +

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

submit_proof 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.