em_submit_evidence · Execution Market MCP: Risk & Policy

WHAT IT DOES

What em_submit_evidence does on Execution Market

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

WHY IT NEEDS A POLICY

Why em_submit_evidence needs a policy

This tool creates/modifies state by recording evidence submissions tied to task completions and financial outcomes (USDC bounty settlements). It is Write rather than Execute because it submits data rather than runs arbitrary code. It is high severity because incorrect or malicious evidence submission could trigger unwarranted payments or disputes in a financial system.

From the tool's definition Tool name em_submit_evidence suggests submission of evidence (likely proofs of work completion for bounty tasks); empty description limits certainty. Context shows gasless USDC payments via x402 and task acceptance/approval workflow.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

em_submit_evidence Rate-limited

em_submit_evidence 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": {
    "em_submit_evidence": {
      "limits": [
        {
          "counter": "em_submit_evidence_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 Execution Market, so you can run agents against it safely.

FAQ

Questions about em_submit_evidence

What does the em_submit_evidence tool do? +

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

How do I enforce a policy on em_submit_evidence? +

Register the Execution Market MCP server in PolicyLayer and add a rule for em_submit_evidence: 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 Execution Market. Nothing to install.

What risk level is em_submit_evidence? +

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

Can I rate-limit em_submit_evidence? +

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

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

em_submit_evidence is provided by the Execution Market MCP server (https://mcp.execution.market/mcp/). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.