@wavespeed/mcp 1.0.10 → 1.0.12

package/README.md

@@ -39,10 +39,34 @@ Built on the same design as the open-source [`@wavespeed/cli`](https://github.co
 | `upload_file` | Local file → hosted URL (24h content-hash dedupe) |
 | `get_prediction` | Status/outputs of any run by id; optional `wait_seconds` to wait for it |
 
-Some generations take minutes to hours. `run_model` waits up to `wait_seconds` (default 50, max 1800) and then returns `done: false` with the prediction id — the task keeps running server-side, and `get_prediction` picks it up. While waiting, both tools send MCP progress notifications that carry the prediction id.
+Some generations take minutes to hours. `run_model` submits the run and returns the prediction id right away (`done: false`); the assistant then calls `get_prediction` with that id and `wait_seconds` (max 1800) until `done` is `true`. The task keeps running server-side, so a dropped connection loses nothing. Pass `wait_seconds` to `run_model` to wait for a quick model in the same call. While waiting, both tools send MCP progress notifications that carry the prediction id.
 
 ## Setup
 
+### Remote (nothing to install)
+
+The same server is hosted at:
+
+```text
+https://api.wavespeed.ai/mcp
+```
+
+- **Claude on the web / ChatGPT:** add a custom connector with that address and approve the connection on the WaveSpeed page that opens. Approving creates a dedicated API key (named `MCP · <app>`) that you can delete on the [API Keys](https://wavespeed.ai/accesskey) page to disconnect.
+- **Claude Code:** `claude mcp add --transport http wavespeed https://api.wavespeed.ai/mcp`
+- **Cursor:**
+  <a href="https://cursor.com/install-mcp?name=wavespeed&config=eyJ1cmwiOiJodHRwczovL2FwaS53YXZlc3BlZWQuYWkvbWNwIn0%3D">
+    <picture>
+      <source media="(prefers-color-scheme: dark)" srcset="https://cursor.com/deeplink/mcp-install-light.svg">
+      <img src="https://cursor.com/deeplink/mcp-install-dark.svg" alt="Add the hosted wavespeed MCP server to Cursor" height="32"/>
+    </picture>
+  </a>
+- **VS Code:** `code --add-mcp '{"name":"wavespeed","type":"http","url":"https://api.wavespeed.ai/mcp"}'`
+- **Any other client that sends request headers:** point it at the URL with `Authorization: Bearer <your API key>`.
+
+The hosted server has the same tools, with one difference for files: it cannot read files on your computer, so pass public URLs, use `create_upload` from a tool that can send HTTP requests (it returns a temporary upload address and the `download_url` to use as an input), or, in ChatGPT, attach the file to the chat (the `upload_attachment` tool, which only ChatGPT can fill, imports it and returns a `download_url`). Full guide: [wavespeed.ai/docs/mcp](https://wavespeed.ai/docs/mcp).
+
+### Local (npx)
+
 Auth resolves from `WAVESPEED_API_KEY`, or from the CLI's stored login (`wavespeed login`) — one login covers both tools. Keys: [wavespeed.ai/accesskey](https://wavespeed.ai/accesskey).
 
 **Claude Code**

package/dist/server.js

@@ -43,13 +43,14 @@ async function uploadFile(filePath) {
     const client = new Client(apiKey, { baseUrl: getBaseUrl(), clientName: MCP_CLIENT_NAME });
     return uploadWithCache(filePath, (p) => client.upload(p));
 }
-// Default wait for run_model. Many MCP clients abort a tool call after 60s,
-// and an aborted call never delivers the prediction id — so return before
-// that with the id in hand. Longer waits are opt-in via wait_seconds.
-const DEFAULT_WAIT_SECONDS = 50;
+// run_model submits and returns the prediction id right away (same as the
+// hosted server); the assistant then waits with get_prediction. Many MCP
+// clients abort a tool call after 60s and an aborted call never delivers the
+// id, so a long wait is opt-in via wait_seconds.
+const DEFAULT_WAIT_SECONDS = 0;
 const POLL_INTERVAL_MS = 2000;
-const STILL_RUNNING_HINT = 'Still running on the server — generations can take minutes to hours. ' +
-    'Call get_prediction with this id (optionally with wait_seconds) to check again.';
+const STILL_RUNNING_HINT = 'The run was submitted and is processing on the server. Call get_prediction with this id and wait_seconds ' +
+    'until done=true; it returns the output URLs. Do not submit the same run again: a new run is billed again.';
 // Emits notifications/progress while polling when the client asked for it.
 // Each one carries the prediction id, and clients that reset their timeout
 // on progress keep a long wait alive.
@@ -154,7 +155,7 @@ export function createServer() {
             property_order: schema?.['x-order-properties'] ?? [],
         });
     });
-    server.tool('run_model', 'Run any WaveSpeed model. input keys come from get_model_schema; unknown keys are rejected before submission. Local files: pass "@./path" string values — they are uploaded and replaced with hosted URLs (bare paths are NOT uploaded). Returns output URLs when done=true. Some generations take minutes to hours: if the wait ends first, the result has done=false and the prediction id — the task keeps running, so check it with get_prediction.', {
+    server.tool('run_model', 'Run any WaveSpeed model. input keys come from get_model_schema; unknown keys are rejected before submission. Local files: pass "@./path" string values — they are uploaded and replaced with hosted URLs (bare paths are NOT uploaded). Returns the prediction id right away (done=false); call get_prediction with that id and wait_seconds until done=true to get the output URLs. The task keeps running on the server. Pass wait_seconds here to wait for a quick model in the same call.', {
         model: z.string().describe('Model ID from list_models'),
         input: z
             .record(z.unknown())
@@ -165,7 +166,7 @@ export function createServer() {
             .min(0)
             .max(1800)
             .default(DEFAULT_WAIT_SECONDS)
-            .describe(`Max seconds to wait before returning the still-running prediction id (default ${DEFAULT_WAIT_SECONDS}); 0 = submit only`),
+            .describe(`Max seconds to wait for the result in this call (default ${DEFAULT_WAIT_SECONDS}: return the prediction id right away)`),
     }, { readOnlyHint: false, destructiveHint: false, idempotentHint: false, openWorldHint: true }, async ({ model, input, wait_seconds }, extra) => {
         const resolved = await resolveLocalFiles(input, {
             upload: async (p) => (await uploadFile(p)).url,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@wavespeed/mcp",
-  "version": "1.0.10",
+  "version": "1.0.12",
   "description": "WaveSpeed MCP server — run any model on the live WaveSpeed catalog (image, video, audio, 3D) with schema introspection, local-file upload, and price quotes.",
   "type": "module",
   "bin": {