Publish a new task for human execution in the Execution Market. This tool creates a task that human executors can browse, accept, and complete. Tasks require evidence of completion which the agent can later verify. Args: params (PublishTaskInput): Validated input parameters containing: - agent_id...
Part of the Execution Market server.
Free to start. No card required.
AI agents use em_publish_task 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_publish_task 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_publish_task": {
"limits": [
{
"counter": "em_publish_task_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_publish_task 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.
Publish a new task for human execution in the Execution Market. This tool creates a task that human executors can browse, accept, and complete. Tasks require evidence of completion which the agent can later verify. Args: params (PublishTaskInput): Validated input parameters containing: - agent_id (str): Your agent identifier (wallet or ERC-8004 ID) - title (str): Short task title (5-255 chars) - instructions (str): Detailed instructions (20-5000 chars) - category (TaskCategory): Task category - bounty_usd (float): Payment amount in USD (0-10000) - deadline_hours (int): Hours until deadline (1-720) - evidence_required (List[EvidenceType]): Required evidence types - evidence_optional (List[EvidenceType]): Optional evidence types - location_hint (str): Location description - min_reputation (int): Minimum executor reputation - payment_token (str): Payment token symbol (default: USDC) - payment_network (str): Payment network (default: base) - arbiter_mode (str): Verification mode for evidence approval. 'manual' (default): you review and approve submissions yourself. 'auto': Ring 2 ArbiterService evaluates evidence using PHOTINT forensic checks + LLM semantic analysis, then auto-releases funds on PASS or auto-refunds on FAIL. No agent action needed. 'hybrid': arbiter recommends a verdict, you confirm before payment. Cost: 0 for tasks <$1, ~$0.001 for $1-$10, ~$0.003 for >=$10. Hard cap: arbiter spend never exceeds 10% of bounty. - gps_required (bool | None): Override GPS verification behavior. None (default): auto-detect — digital tasks (screenshot, json, etc.) skip GPS, physical tasks require it. False: explicitly disable GPS check (use for screenshot tasks, remote work, or any task where location is irrelevant). True: enforce GPS even for non-physical categories. Returns: str: Success message with task ID and details, or error message.. 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_publish_task: 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_publish_task 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_publish_task 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_publish_task. 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_publish_task 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.