--- title: Tasks description: Run long-running tool invocations asynchronously with status polling and input requests. uid: tasks --- ## Tasks Tasks let an MCP server run a request asynchronously and report its result to the client later. The primary use case today is long-running tool invocations: the tool is offloaded to a background task, and the client polls for status, optionally exchanging additional input along the way. Tasks are provided by the `ModelContextProtocol.Extensions.Tasks` package and require MCP protocol version `2026-07-28` or later. The implementation follows [SEP-2663 (Tasks Extension)](https://github.com/modelcontextprotocol/modelcontextprotocol/blob/main/seps/2663-tasks-extension.md). ### Compatibility with v1 experimental Tasks The Tasks extension in v2.0.0 replaces the experimental Tasks implementation shipped in v1.3.0 and v1.4.x. The implementations are not compatible at either the API or protocol level. A v2 Tasks client or server must use a connection negotiated to `2026-07-28` or later; it cannot fall back to the down-level implementation. On a connection negotiated to the down-level `2025-11-25` protocol: - A v2 client calling a v1 server receives an ordinary tool result. The v2 client does not opt in to the down-level Tasks protocol, and `GetTaskAsync` rejects use before a `2026-07-28` connection is negotiated. - A v1 client calling a v2 server likewise receives an ordinary tool result. The v2 server does not create Tasks on a down-level connection, and its `tasks/get` endpoint rejects the legacy request with a method-not-found error. Upgrade both peers to the v2 Tasks extension before using Tasks. The extension provides no compatibility bridge for the previous experimental API. ### Overview A client opts into tasks on a per-request basis by including the `io.modelcontextprotocol/tasks` extension key in the request's `_meta`. When that opt-in is present, the server **might** respond with a instead of the standard result (for example, ). The client then polls `tasks/get` until the task reaches a terminal state. Per the SEP, the server **must not** return `CreateTaskResult` for a request that did not include the extension opt-in. The SDK enforces this on the server side. #### Task lifecycle ```text ┌─────────────────────────┐ ▼ │ (start) → Working ──→ InputRequired │ │ │ │ │ └──────────────┘ (client responds via tasks/update) │ ├──→ Completed (terminal — includes tool results with isError: true) ├──→ Cancelled (terminal) └──→ Failed (terminal — JSON-RPC errors only) ``` wire values are serialized in snake_case: `working`, `input_required`, `completed`, `cancelled`, `failed`. The discriminator field on the response payload is `"task"` for and `"complete"` for ordinary results. ### Server configuration #### Using the task store The easiest way to enable the package's task store integration is to call on the server builder, passing an . The SDK ships for development and tests: ```csharp using ModelContextProtocol.Extensions.Tasks; builder.Services.AddMcpServer() .WithTools() .WithTasks(new InMemoryMcpTaskStore()); ``` When tasks are enabled with `WithTasks` the SDK automatically: - Wires the `tasks/get`, `tasks/update`, and `tasks/cancel` handlers from the store. - Advertises the `io.modelcontextprotocol/tasks` extension in . - Wraps each `[McpServerTool]` invocation so that, when the client opts in to the extension, the tool is offloaded to a background task tracked by the store. - Establishes a task scope so that , , and called from inside the tool surface as entries in the task's `inputRequests` instead of as direct JSON-RPC requests. - Plumbs a `CancellationToken` through to the tool that fires when the client invokes `tasks/cancel`, so cancellation propagates cooperatively. Alternate-result `tools/call` filters run in registration order, with the Tasks filter creating a task at its position in that order. Filters before Tasks run before task creation. Filters after Tasks run in the background before the ordinary filter pipeline. ASP.NET Core tool authorization uses an alternate-result filter registered before Tasks, so an unauthorized call does not create a task. Ordinary `tools/call` filters still run exactly once for task-backed calls. They execute in the background after the task record is created and before the tool body, so validation and telemetry continue to apply. Each background invocation gets an independent DI scope that remains alive until the tool pipeline completes. For production scenarios that need durability, session isolation, multi-process routing, or TTL-based cleanup, implement yourself (see the [Implementing a custom task store](#implementing-a-custom-task-store) section). #### Returning a task from a tool handler For full control without the store's auto-wrapping, set . It returns a , so each invocation can choose between an immediate result and an alternate result such as a : ```csharp using ModelContextProtocol.Extensions.Tasks; options.Handlers.CallToolWithAlternateHandler = async (context, ct) => { if (ShouldRunInline(context.Params!)) { return new CallToolResult { Content = [/* … */] }; } var taskId = await StartBackgroundWorkAsync(context.Params!, ct); var created = new CreateTaskResult { TaskId = taskId, Status = McpTaskStatus.Working, CreatedAt = DateTimeOffset.UtcNow, LastUpdatedAt = DateTimeOffset.UtcNow, PollIntervalMs = 1000, }; return new ResultOrAlternate(created, McpTasksJsonContext.Default.CreateTaskResult); }; ``` > This low-level handler is mutually exclusive with `WithTasks`. When a store is configured, the > SDK does the wrapping for you and throws `InvalidOperationException` if the alternate handler also > returns an alternate. Use one mechanism or the other. When you return a task this way, you're also > responsible for serving `tasks/get`, `tasks/update`, and `tasks/cancel`, which the store provides > automatically. > > and > are mutually exclusive. Setting one while the other is already non-null throws > `InvalidOperationException` at the property setter. ### Client usage #### Automatic polling handles the full task lifecycle automatically: - Injects the `io.modelcontextprotocol/tasks` extension capability into the request's `_meta`. - Polls `tasks/get` at the cadence the server suggests via `pollIntervalMs`. - Dispatches input requests through the client's registered handlers ( and ). - Deduplicates already-resolved input request keys across polls so each request is handled at most once. - Returns the final when the task completes, or throws on `Failed`/`Cancelled`. ```csharp using ModelContextProtocol.Extensions.Tasks; var result = await client.CallToolWithPollingAsync( new CallToolRequestParams { Name = "long-running-tool", Arguments = arguments }, cancellationToken: cancellationToken); ``` #### Manual control Use to receive the raw without auto-polling, then drive the lifecycle yourself using , , and : ```csharp using ModelContextProtocol.Extensions.Tasks; var raw = await client.CallToolAsTaskAsync(requestParams, cancellationToken); if (raw.IsTask) { var taskId = raw.TaskCreated!.TaskId; while (true) { await Task.Delay(TimeSpan.FromMilliseconds(raw.TaskCreated.PollIntervalMs ?? 1000), cancellationToken); var state = await client.GetTaskAsync(taskId, cancellationToken); // Handle InputRequiredTaskResult by calling UpdateTaskAsync, // CompletedTaskResult by deserializing its Result property, etc. } } ``` #### Stuck-task detector `CallToolWithPollingAsync` includes a safety net for misbehaving servers: if the task stays in across many consecutive polls without exposing any new input request keys (that is, every previously requested input has already been resolved by the client and yet the server keeps returning `InputRequired`), the client gives up, issues a best-effort `tasks/cancel`, and throws . This guards against a server that never transitions out of `InputRequired` and prevents an unbounded poll loop. The threshold defaults to `60` consecutive stuck polls and is configurable via the `maxConsecutiveStuckPolls` parameter on `CallToolWithPollingAsync`. The effective wall-clock timeout is roughly `maxConsecutiveStuckPolls * pollIntervalMs`, so tune the value with the server-side poll cadence in mind. Setting it too low risks false positives for servers that are slow to surface follow-up input requests; setting it too high can mask misbehaving servers. ### Input requests (multi-round-trip) When a task needs additional input from the client, the server transitions it to and returns the outstanding requests in . Each entry is an arbitrary key paired with a `{ method, params }` envelope representing an equivalent standalone server-to-client request. The client provides answers via , keyed by the same identifiers. Supported input request methods: | Method | Dispatched to the client handler | | --- | --- | | `elicitation/create` | | | `sampling/createMessage` | | Per SEP-2663: - Each input request key **must** be unique over the lifetime of the task. - Clients **should** deduplicate keys across polls so a request is only presented to the user or model once. `CallToolWithPollingAsync` does this automatically. - Servers **should** ignore `inputResponses` entries whose key does not currently correspond to an outstanding request, including responses for terminal-state tasks. follows this rule. ### Implementing a custom task store Implement for production scenarios. Key requirements drawn from the SEP and the SDK contract: 1. **Thread safety** — every method can be called concurrently. 2. **Idempotent terminal transitions** — , , and must be no-ops on a task that is already in a terminal state so a late cancellation cannot overwrite a result. 3. **`InputResponseReceived` event** — after persisting an input response inside , raise for each resolved entry. This is the only mechanism that wakes a pending `server.ElicitAsync`/`server.SampleAsync` call waiting inside a task scope. In distributed deployments where a different server instance receives the `tasks/update`, the event must be propagated to the originating server (for example via Redis pub/sub, SignalR, or a custom transport). 4. **Strong-consistency on `CreateTaskAsync`** — must not return until the task is durably persisted, so that a subsequent with the returned task ID resolves immediately — even from a different process or node. Stores backed by eventually consistent storage must wait for the write to become visible (quorum acknowledgement, write-through, etc.) before returning. Required by SEP-2663 §306. 5. **Singleton under stateless HTTP** — when the server runs in stateless mode (each request spins up a fresh server instance), the same `IMcpTaskStore` instance must be shared across requests — either by registering it as a singleton in DI, or by backing it with external storage that every instance can reach. Otherwise `tasks/get` polls from subsequent requests will see an empty in-memory store and never find the task. ```csharp public sealed class MyTaskStore : IMcpTaskStore { public event Action? InputResponseReceived; public async Task ResolveInputRequestsAsync( string taskId, IDictionary inputResponses, CancellationToken cancellationToken = default) { // 1. Atomically persist the resolved requests, ignoring keys that are no longer // outstanding or that target a terminal task. await PersistResolvedResponsesAsync(taskId, inputResponses, cancellationToken); // 2. Then notify subscribers so any awaiting server.ElicitAsync/SampleAsync resumes. foreach (var kvp in inputResponses) { InputResponseReceived?.Invoke(new InputResponseReceivedEventArgs { TaskId = taskId, RequestId = kvp.Key, Response = kvp.Value, }); } } // … other IMcpTaskStore members } ``` ### Status semantics is the terminal status whenever the underlying request produced its standard result, *including a with `IsError = true`*. Per SEP-2663, tool-level error results are not promoted to `Failed`. is reserved for JSON-RPC protocol-level errors during execution — for example, a malformed request, or an unhandled exception in a custom handler that the SDK converts to a JSON-RPC error. Use for domain-level errors the model should see. ### Cancellation semantics Per SEP-2663, `tasks/cancel` is **eventually consistent and cooperative**: the server acknowledges the request immediately, but is not required to actually stop the work or to transition to `Cancelled`. The notifications-cancelled mechanism (used for plain JSON-RPC requests) is not used for task cancellation; clients must use `tasks/cancel`. In the built-in SDK pipeline, when a task is wrapped by a configured `TaskStore`: 1. The store's `SetCancelledAsync` transitions the task to `Cancelled` (a no-op if the task is already terminal). 2. The associated `CancellationTokenSource` is signaled, propagating cancellation to the tool's `CancellationToken` so cooperative cleanup can run. 3. Whichever side (the cancel handler or the background runner's `finally` block) wins `TryRemove` on the cancellation source owns disposal, avoiding `ObjectDisposedException`. ### Architecture notes #### Immutable store design uses immutable record snapshots with compare-and-swap updates for lock-free thread safety. `InputRequests` and `InputResponses` are exposed as `ImmutableDictionary<,>` so observers can't mutate internal state. #### Capability bypass inside a task scope When `server.ElicitAsync`/`server.SampleAsync`/`server.RequestRootsAsync` execute inside a task scope, the SDK intentionally skips the normal client-capability negotiation checks (`ThrowIfElicitationUnsupported`, etc.). The tasks extension itself is the negotiated capability: the client opted in by including the extension marker in the originating request, so it's responsible for handling — or rejecting — the input requests surfaced through `tasks/get`. ### Known limitations - **Server-push task status notifications (SEP-2575)**: not yet implemented. Clients rely on polling exclusively. - **Lazy task creation**: when a tool runs through the task store, the store's is invoked eagerly before the inner handler runs, so tools that complete inline still incur a store write. There is currently no built-in deferral. - **Mid-execution promotion to task**: an `[McpServerTool]` method cannot start executing synchronously and then transition its remaining work to a background task. Use a custom if you need that pattern. - **`roots/list` as an input request**: the server SDK routes `RequestRootsAsync` through the task channel when called from inside a task scope, but the client SDK does not currently dispatch a handler for that method. Avoid calling `server.RequestRootsAsync` from within a task scope until client-side support is added. - **`ServerCapabilities.Extensions` round-trip**: the dictionary is typed as `IDictionary` so its values cannot be deserialized by the source generator. The negotiated extension surfaces correctly at the wire level, but round-tripping arbitrary extension payloads in-process is not supported.