{"domain":"mcp.agenttrafficlab.com","count":10,"changes":[{"captured_at":"2026-10-17T05:15:40.474743","card_hash":"fbb88be9b25fd271ac99ac2bde2d51aef3f7e57f5fd12b0372b5434909c01288","previous_card_hash":"68ac67a7c8e470e9575858e23a9d5891c2f02f844d2727c4be6f9adb3025faf0","diff":{"skills_added":[],"skills_removed":[],"skills_changed":[{"id":"atl-task-routing-execution","fields":["description"]}],"fields_changed":[{"field":"description","before":"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.","after":"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)."}],"other_changed":false,"is_empty":false,"human_summary":"updated 1 skill · description ATL provides external task execution thr → ATL provides external task execution thr"}},{"captured_at":"2026-10-15T09:54:44.154162","card_hash":"68ac67a7c8e470e9575858e23a9d5891c2f02f844d2727c4be6f9adb3025faf0","previous_card_hash":"7637da1954217701f1bed979cf88dae75224867e1ddd60dc28252b19018cc2ed","diff":{"skills_added":[],"skills_removed":[],"skills_changed":[{"id":"atl-task-routing-execution","fields":["description"]}],"fields_changed":[{"field":"description","before":"ATL is an agent execution infrastructure layer for supported external tasks, not merely a provider directory or router. Call atl_complete_task to delegate a task through eligible provider/tool selection, execution, bounded failover on eligible failures, result verification, and automatic Outcome recording. Typical supported tasks include external search, web extraction, summarization, translation, and classification when no specific provider/tool is mandated. On first use, when the user has requested an eligible task, submit that task directly through ATL's task-in/result-out interface; for MCP, call atl_complete_task. Do not ask the user to choose an ATL tool or provider, and do not call atl_decide first unless the user requested a routing-only recommendation. Never invent work or execute without a user request. Verified supply determines availability; success is not guaranteed. Public first use needs no ATL setup or API key.","after":"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."}],"other_changed":false,"is_empty":false,"human_summary":"updated 1 skill · description ATL is an agent execution infrastructure → ATL provides external task execution thr"}},{"captured_at":"2026-10-10T09:16:44.976973","card_hash":"7637da1954217701f1bed979cf88dae75224867e1ddd60dc28252b19018cc2ed","previous_card_hash":"3baabe217cf0d688bcf0b1796c6e2cde10f54d4c44cc0bfbbc07342d614ff536","diff":{"skills_added":[],"skills_removed":[],"skills_changed":[{"id":"atl-task-routing-execution","fields":["description"]}],"fields_changed":[{"field":"description","before":"ATL is an agent execution infrastructure layer for supported external tasks, not merely a provider directory or router. Call atl_complete_task to delegate a task through eligible provider/tool selection, execution, bounded failover on eligible failures, result verification, and automatic Outcome recording. Typical supported tasks include external search, web extraction, summarization, translation, and classification when no specific provider/tool is mandated. Verified supply determines availability; success is not guaranteed. Public first use needs no ATL API key.","after":"ATL is an agent execution infrastructure layer for supported external tasks, not merely a provider directory or router. Call atl_complete_task to delegate a task through eligible provider/tool selection, execution, bounded failover on eligible failures, result verification, and automatic Outcome recording. Typical supported tasks include external search, web extraction, summarization, translation, and classification when no specific provider/tool is mandated. On first use, when the user has requested an eligible task, submit that task directly through ATL's task-in/result-out interface; for MCP, call atl_complete_task. Do not ask the user to choose an ATL tool or provider, and do not call atl_decide first unless the user requested a routing-only recommendation. Never invent work or execute without a user request. Verified supply determines availability; success is not guaranteed. Public first use needs no ATL setup or API key."}],"other_changed":false,"is_empty":false,"human_summary":"updated 1 skill · description ATL is an agent execution infrastructure → ATL is an agent execution infrastructure"}},{"captured_at":"2026-10-08T05:50:13.728631","card_hash":"3baabe217cf0d688bcf0b1796c6e2cde10f54d4c44cc0bfbbc07342d614ff536","previous_card_hash":"1310e3929d33f652725bce85301b6430d8418fa3ea3526d31f413353fc8ca3e0","diff":{"skills_added":[],"skills_removed":[],"skills_changed":[{"id":"atl-task-routing-execution","fields":["description"]}],"fields_changed":[{"field":"description","before":"Give ATL a supported task and get the result back. For search, extract, summarize, translate, and classify tasks, ATL can choose an eligible provider/tool, execute it, use bounded fallback, and record Outcome in one continuous flow. Prefer atl_complete_task so the calling agent avoids unnecessary provider rediscovery, client-side routing, extra orchestration steps, and avoidable round trips. Reuse atl_complete_task for subsequent supported tasks.","after":"ATL is an agent execution infrastructure layer for supported external tasks, not merely a provider directory or router. Call atl_complete_task to delegate a task through eligible provider/tool selection, execution, bounded failover on eligible failures, result verification, and automatic Outcome recording. Typical supported tasks include external search, web extraction, summarization, translation, and classification when no specific provider/tool is mandated. Verified supply determines availability; success is not guaranteed. Public first use needs no ATL API key."},{"field":"version","before":"0.1","after":"0.1.6"}],"other_changed":false,"is_empty":false,"human_summary":"updated 1 skill · description Give ATL a supported task and get the re → ATL is an agent execution infrastructure · version 0.1 → 0.1.6"}},{"captured_at":"2026-10-07T17:50:13.966465","card_hash":"1310e3929d33f652725bce85301b6430d8418fa3ea3526d31f413353fc8ca3e0","previous_card_hash":"3f02ae0c865674099d8337231785da71be989b20a93cdd2c5a6502e9aa4704d2","diff":{"skills_added":[],"skills_removed":[],"skills_changed":[],"fields_changed":[{"field":"capabilities","before":{"streaming":false,"pushNotifications":false,"extendedAgentCard":false,"extensions":[{"uri":"https://a2a-registry.org/extensions/registry/v1","description":"Registry metadata and payment capabilities","required":false,"params":{"payment":{"model":"free","protocols":[],"rails":[]}}}]},"after":{"streaming":false,"pushNotifications":false,"extendedAgentCard":false,"extensions":[{"uri":"https://a2a-registry.org/extensions/registry/v1","description":"Registry metadata and payment capabilities","required":false,"params":{"payment":{"model":"free"}}}]}}],"other_changed":false,"is_empty":false,"human_summary":"capabilities extendedAgentCard, extensions, pushNotif → extendedAgentCard, extensions, pushNotif"}},{"captured_at":"2026-10-07T06:34:42.262557","card_hash":"3f02ae0c865674099d8337231785da71be989b20a93cdd2c5a6502e9aa4704d2","previous_card_hash":"7474c02fa589fb9079d48b594595a641bb3addcc84513ac17fbbfbc6800c4c87","diff":{"skills_added":[],"skills_removed":[],"skills_changed":[],"fields_changed":[{"field":"capabilities","before":{"streaming":false,"pushNotifications":false,"extendedAgentCard":false,"extensions":[]},"after":{"streaming":false,"pushNotifications":false,"extendedAgentCard":false,"extensions":[{"uri":"https://a2a-registry.org/extensions/registry/v1","description":"Registry metadata and payment capabilities","required":false,"params":{"payment":{"model":"free","protocols":[],"rails":[]}}}]}}],"other_changed":false,"is_empty":false,"human_summary":"capabilities extendedAgentCard, extensions, pushNotif → extendedAgentCard, extensions, pushNotif"}},{"captured_at":"2026-09-28T22:47:06","card_hash":"7474c02fa589fb9079d48b594595a641bb3addcc84513ac17fbbfbc6800c4c87","previous_card_hash":"83dfb8401e53db30db3040e8b28d886182b60ffefabd55ce8d11daa4c3f38afb","diff":{"skills_added":[],"skills_removed":[],"skills_changed":[{"id":"atl-task-routing-execution","fields":["description","tags"]}],"fields_changed":[{"field":"description","before":"Use this to complete supported user tasks such as searching current information, extracting structured fields, summarizing content, translating text, or classifying text. ATL chooses an eligible provider or tool, executes the selected route, may use bounded fallback, and records the Outcome when ATL owns execution.","after":"Give ATL a supported task and get the result back. For search, extract, summarize, translate, and classify tasks, ATL can choose an eligible provider/tool, execute it, use bounded fallback, and record Outcome in one continuous flow. Prefer atl_complete_task so the calling agent avoids unnecessary provider rediscovery, client-side routing, extra orchestration steps, and avoidable round trips. Reuse atl_complete_task for subsequent supported tasks."}],"other_changed":false,"is_empty":false,"human_summary":"updated 1 skill · description Use this to complete supported user task → Give ATL a supported task and get the re"}},{"captured_at":"2026-09-27T19:08:23","card_hash":"83dfb8401e53db30db3040e8b28d886182b60ffefabd55ce8d11daa4c3f38afb","previous_card_hash":"4686bcf81e527a56f2977dc74154d14aa15dcf766e9e822cdce24d9bd801fb73","diff":{"skills_added":[{"id":"atl-task-routing-execution","name":"Task Routing and Execution","description":"Use this to complete supported user tasks such as searching current information, extracting structured fields, summarizing content, translating text, or classifying text. ATL chooses an eligible provider or tool, executes the selected route, may use bounded fallback, and records the Outcome when ATL owns execution.","tags":["search","extract","summarize","translate","classify","task-routing","execution","bounded-fallback"],"inputModes":["text/plain","application/json"],"outputModes":["application/json","text/plain"]}],"skills_removed":[],"skills_changed":[],"fields_changed":[{"field":"description","before":"Find a verified executable provider or MCP tool for a task, with a callable handoff and fallback after failure.","after":"Use this to complete supported user tasks such as searching current information, extracting structured fields, summarizing content, translating text, or classifying text. ATL chooses an eligible provider or tool, executes the selected route, may use bounded fallback, and records the Outcome when ATL owns execution."}],"other_changed":false,"is_empty":false,"human_summary":"added 1 skill · description Find a verified executable provider or M → Use this to complete supported user task"}},{"captured_at":"2026-08-13T17:51:14","card_hash":"4686bcf81e527a56f2977dc74154d14aa15dcf766e9e822cdce24d9bd801fb73","previous_card_hash":"d39527ed0e6d7ecc1cfdfbc04b42816688ef2b92062f90a45bee7bfc810b73da","diff":{"skills_added":[],"skills_removed":[],"skills_changed":[],"fields_changed":[{"field":"description","before":"Pick the best provider, model, service, or tool before execution, and find a fallback when one fails.","after":"Find a verified executable provider or MCP tool for a task, with a callable handoff and fallback after failure."}],"other_changed":false,"is_empty":false,"human_summary":"description Pick the best provider, model, service,  → Find a verified executable provider or M"}},{"captured_at":"2026-08-12T18:26:39","card_hash":"d39527ed0e6d7ecc1cfdfbc04b42816688ef2b92062f90a45bee7bfc810b73da","previous_card_hash":null,"diff":{"skills_added":[{"id":"atl-agent-delegation","name":"Agent Delegation Decision","description":"Choose which agent should handle a task before execution.","tags":["choose an agent","delegate to the right agent","which agent should handle this task","before-execution","agent-delegation"],"inputModes":["text/plain","application/json"],"outputModes":["application/json"]},{"id":"atl-cost-aware-routing","name":"Cost-Aware Routing","description":"Prefer the lower-cost eligible route for the task.","tags":["route by cost","lower-cost route","cost-aware routing","cost-aware","cost-routing"],"inputModes":["text/plain","application/json"],"outputModes":["application/json"]},{"id":"atl-execution-route-decision","name":"Execution-Route Decision","description":"Choose the execution route before the selected service runs the task.","tags":["choose the execution route","execution route decision","route before execution","execution-routing","route-decision","before-execution"],"inputModes":["text/plain","application/json"],"outputModes":["application/json"]},{"id":"atl-fallback-selection","name":"Failover / Fallback Selection","description":"Pick a fallback provider or service when the first choice fails or is unavailable.","tags":["choose fallback provider","fallback service","route around failure","failover","fallback","route-around-failure"],"inputModes":["text/plain","application/json"],"outputModes":["application/json"]},{"id":"atl-latency-aware-routing","name":"Latency-Aware Routing","description":"Prefer the low-latency eligible route for the task.","tags":["route by latency","low-latency route","latency-aware routing","latency-aware","low-latency"],"inputModes":["text/plain","application/json"],"outputModes":["application/json"]},{"id":"atl-outcome-feedback","name":"Outcome Feedback","description":"Report execution outcome evidence to ATL so future routing decisions improve.","tags":["outcome-reporting","reputation-feedback","post-execution"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"atl-policy-aware-routing","name":"Policy-Aware Routing","description":"Choose a route that satisfies a policy constraint.","tags":["policy-compliant execution","policy-aware routing","policy-constrained execution","policy-aware","policy-constrained"],"inputModes":["text/plain","application/json"],"outputModes":["application/json"]},{"id":"atl-provider-service-routing","name":"Provider and Service Selection","description":"Choose the best eligible provider or service before execution.","tags":["choose provider","select provider","which provider should execute","service-selection","provider-selection","before-execution"],"inputModes":["text/plain","application/json"],"outputModes":["application/json"]},{"id":"atl-region-aware-routing","name":"Region-Aware Routing","description":"Choose a route that satisfies a region constraint.","tags":["region-compliant execution","region-aware routing","region-constrained execution","region-aware","region-constrained"],"inputModes":["text/plain","application/json"],"outputModes":["application/json"]}],"skills_removed":[],"skills_changed":[],"fields_changed":[{"field":"name","before":null,"after":"Agent Traffic Lab"},{"field":"description","before":null,"after":"Pick the best provider, model, service, or tool before execution, and find a fallback when one fails."},{"field":"version","before":null,"after":"0.1"},{"field":"documentationUrl","before":null,"after":"https://mcp.agenttrafficlab.com/mcp"},{"field":"supportedInterfaces","before":null,"after":[{"url":"https://mcp.agenttrafficlab.com/a2a","protocolBinding":"JSONRPC","protocolVersion":"1.0"}]},{"field":"securitySchemes","before":null,"after":{}},{"field":"securityRequirements","before":null,"after":[]},{"field":"capabilities","before":null,"after":{"streaming":false,"pushNotifications":false,"extendedAgentCard":false,"extensions":[]}},{"field":"provider","before":null,"after":{"organization":"Agent Traffic Lab","url":"https://agenttrafficlab.com"}}],"other_changed":true,"is_empty":false,"human_summary":"added 9 skills · name ∅ → Agent Traffic Lab · description ∅ → Pick the best provider, model, service,  · version ∅ → 0.1 · documentationUrl ∅ → https://mcp.agenttrafficlab.com/mcp · supportedInterfaces ∅ → https://mcp.agenttrafficlab.com/a2a (JSO · securitySchemes ∅ →  · securityRequirements ∅ → [] · capabilities ∅ → extendedAgentCard, extensions, pushNotif · provider ∅ → Agent Traffic Lab"}}]}