# Agent Traffic Lab

> ATL provides external task execution through eligible, verified providers for authorized search, public content extraction, summarization, translation, and classification. Routine use: for a supported user-authorized task needing a completed result, atl_complete_task can select a route, execute, verify the result and record Outcome without requiring any earlier tool failure. Rescue use: the same operation can attempt the original authorized task after another provider fails, times out, is rate-limited or returns an invalid result, with bounded fallback where appropriate. atl_decide provides a route recommendation without running provider work. A task must be user-authorized and within scope. Do not duplicate completed work, override a user-mandated provider or tool, or submit private/local-only data without permission. Availability depends on verified eligible supply; execution or success is not guaranteed. The initial public path does not require an ATL account or API key. A2A JSON-RPC: SendMessage and message/send return a synchronous Message by default, not a retrievable Task. Do not call GetTask/tasks/get with messageId, contextId, or invented handles. Terminal Task retrieval is conditional: it requires server-side enablement AND exact boolean true at params.metadata.atlTerminalTask on the SendMessage request. Only query an actual Task ID returned by ATL (v1 result.task.id or v0.3 result.id); issued Task handles expire after 300 seconds. Unknown or expired IDs receive TaskNotFound (-32001, HTTP 404).

- **Domain**: `mcp.agenttrafficlab.com`
- **Provider**: Agent Traffic Lab (https://agenttrafficlab.com)
- **A2A protocol version**: 1.0
- **Kind**: a2a_agent
- **Live-responds (last probe)**: True
- **Signed card**: True
- **Streaming**: False
- **Quality score**: 100%

## Skills
- **Task Routing and Execution** — ATL provides external task execution through eligible, verified providers for authorized search, public content extraction, summarization, translation, and clas
- **Agent Delegation Decision** — Choose which agent should handle a task before execution.
- **Provider and Service Selection** — Choose the best eligible provider or service before execution.
- **Execution-Route Decision** — Choose the execution route before the selected service runs the task.
- **Failover / Fallback Selection** — Pick a fallback provider or service when the first choice fails or is unavailable.
- **Cost-Aware Routing** — Prefer the lower-cost eligible route for the task.
- **Latency-Aware Routing** — Prefer the low-latency eligible route for the task.
- **Region-Aware Routing** — Choose a route that satisfies a region constraint.
- **Policy-Aware Routing** — Choose a route that satisfies a policy constraint.
- **Outcome Feedback** — Report execution outcome evidence to ATL so future routing decisions improve.

## URLs
- Agent card: https://mcp.agenttrafficlab.com/.well-known/agent-card.json
- Page (HTML): https://agenstry.com/agents/mcp.agenttrafficlab.com
- Documentation: https://mcp.agenttrafficlab.com/mcp