submit_errand
Submit an async job that runs off your context; returns a job_id immediately. type='fetch_bundle' (fetch up to 8 URLs into one artifact), 'delay' (ping a callback in N seconds), or 'deep_research' (multi-round web search → render → refine → a cited markdown report artifact, ~1–2 min; poll check_e...
This record as markdown: /tools/com-wingmanprotocol-agent-gateway/submit-errand.md
What submit_errand does on Gateway
AI agents invoke submit_errand to trigger actions in Gateway. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
type | string | Yes | |
handle | string | — | |
inputs | object | Yes | fetch_bundle: {urls:[...]}; delay: {seconds:N}; deep_research: {query:str, max_rounds?:1-3} |
secret | string | — | |
callback_url | string | — | optional completion webhook |
Parameters from the server's own tool schema.
Why submit_errand is rated High
This tool triggers external async operations — fetching URLs, invoking callbacks, and performing multi-round web searches — all of which have external side effects dependent on the arguments provided. It spans Execute territory clearly.
From the tool's definition 'Submit an async job that runs off your context'; types include 'fetch_bundle' (fetch up to 8 URLs), 'delay' (ping a callback), 'deep_research' (multi-round web search → render → refine → cited markdown report)
Risk signalsAccepts URL/endpoint input (callback_url) · Handles credentials or secrets (secret)
Attacks that exploit this kind of access
The rule that runs submit_errand safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Gateway, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For submit_errand, this is the rule to start with:
submit_errand stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Gateway, apply this rule, and every submit_errand call is checked against it from then on.
Questions about submit_errand
Submit an async job that runs off your context; returns a job_id immediately. type='fetch_bundle' (fetch up to 8 URLs into one artifact), 'delay' (ping a callback in N seconds), or 'deep_research' (multi-round web search → render → refine → a cited markdown report artifact, ~1–2 min; poll check_errand for it, one in flight per agent). It is categorised as a Execute tool in the Gateway MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
submit_errand accepts 5 parameters: type, handle, inputs, secret, callback_url. Required: type, inputs. The full parameter table on this page comes from the server's own tool schema.
Register the Gateway MCP server in PolicyLayer and add a rule for submit_errand: 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 Gateway. Nothing to install.
submit_errand is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the submit_errand 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 submit_errand. 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.
submit_errand is provided by the Gateway MCP server (https://wingmanprotocol.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Gateway, and thousands of servers like it.
Across the catalogue