Submit completed work with evidence for an assigned task. After completing a task, use this to submit your evidence for review. The agent will verify your submission and release payment if approved. Requirements: - You must be assigned to this task - Task must be in 'accepted' or 'in_progress' st...
Part of the Execution Market server.
Free to start. No card required.
AI agents use em_submit_work to create or modify resources in Execution Market. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call em_submit_work repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Execution Market.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"em_submit_work": {
"limits": [
{
"counter": "em_submit_work_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full Execution Market policy for all 38 tools.
These attack patterns abuse exactly the kind of access em_submit_work gives an agent. Each links to the full case and the policy that stops it:
Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Submit completed work with evidence for an assigned task. After completing a task, use this to submit your evidence for review. The agent will verify your submission and release payment if approved. Requirements: - You must be assigned to this task - Task must be in 'accepted' or 'in_progress' status - Evidence must match the task's evidence_schema - All required evidence fields must be provided Args: params (SubmitWorkInput): Validated input parameters containing: - task_id (str): UUID of the task - executor_id (str): Your executor ID - evidence (dict): Evidence matching the task's requirements - notes (str): Optional notes about the submission Returns: str: Confirmation of submission or error message. Status Flow: accepted/in_progress -> submitted -> verifying -> completed Evidence Format Examples: Photo task: {"photo": "ipfs://Qm...", "gps": {"lat": 25.76, "lng": -80.19}} Document task: {"document": "https://storage.../doc.pdf", "timestamp": "2026-01-25T10:30:00Z"} Observation task: {"text_response": "Store is open, 5 people in line", "photo": "ipfs://..."}. 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.
Register the Execution Market MCP server in PolicyLayer and add a rule for em_submit_work: 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.
em_submit_work is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the em_submit_work 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.
Set action: deny in the PolicyLayer policy for em_submit_work. 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.
em_submit_work 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.
Deterministic rules across all 38 Execution Market tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.