@mastra/mcp-docs-server 0.13.46-alpha.1 → 0.13.46-alpha.2

package/.docs/organized/changelogs/%40mastra%2Fclient-js.md

@@ -1,5 +1,18 @@
 # @mastra/client-js
 
+## 0.17.0-alpha.2
+
+### Patch Changes
+
+- The client-js package had its own simpler zodToJsonSchema implementation that was missing critical features from schema-compat. This could cause issues when users pass Zod schemas with `z.record()` or `z.date()` through the MastraClient. ([#10925](https://github.com/mastra-ai/mastra/pull/10925))
+
+  Now the client uses the same implementation as the rest of the codebase, which includes the Zod v4 `z.record()` bug fix, date-time format conversion for `z.date()`, and proper handling of unrepresentable types.
+
+  Also removes the now-unused `zod-to-json-schema` dependency from client-js.
+
+- Updated dependencies [[`b685c9c`](https://github.com/mastra-ai/mastra/commit/b685c9c0b89f49e0d4542c4ac72569682db69794)]:
+  - @mastra/core@0.24.7-alpha.2
+
 ## 0.17.0-alpha.1
 
 ### Minor Changes
@@ -486,17 +499,4 @@
 
 ## 0.15.0-alpha.0
 
-### Minor Changes
-
-- Breaking change to move the agent.streamVNext/generateVNext implementation to the default stream/generate. The old stream/generate have now been moved to streamLegacy and generateLegacy ([#8097](https://github.com/mastra-ai/mastra/pull/8097))
-
-### Patch Changes
-
-- Fix an issue preventing showing working memory and semantic recall in the playground ([#8358](https://github.com/mastra-ai/mastra/pull/8358))
-
-- Add observe strean to get streans after workflow has been interrupted ([#8318](https://github.com/mastra-ai/mastra/pull/8318))
-
-- Updated dependencies [[`00cb6bd`](https://github.com/mastra-ai/mastra/commit/00cb6bdf78737c0fac14a5a0c7b532a11e38558a), [`869ba22`](https://github.com/mastra-ai/mastra/commit/869ba222e1d6b58fc1b65e7c9fd55ca4e01b8c2f), [`1b73665`](https://github.com/mastra-ai/mastra/commit/1b73665e8e23f5c09d49fcf3e7d709c75259259e), [`f7d7475`](https://github.com/mastra-ai/mastra/commit/f7d747507341aef60ed39e4b49318db1f86034a6), [`084b77b`](https://github.com/mastra-ai/mastra/commit/084b77b2955960e0190af8db3f77138aa83ed65c), [`a93ff84`](https://github.com/mastra-ai/mastra/commit/a93ff84b5e1af07ee236ac8873dac9b49aa5d501), [`bc5aacb`](https://github.com/mastra-ai/mastra/commit/bc5aacb646d468d325327e36117129f28cd13bf6), [`6b5af12`](https://github.com/mastra-ai/mastra/commit/6b5af12ce9e09066e0c32e821c203a6954498bea), [`bf60e4a`](https://github.com/mastra-ai/mastra/commit/bf60e4a89c515afd9570b7b79f33b95e7d07c397), [`d41aee5`](https://github.com/mastra-ai/mastra/commit/d41aee526d124e35f42720a08e64043229193679), [`e8fe13c`](https://github.com/mastra-ai/mastra/commit/e8fe13c4b4c255a42520127797ec394310f7c919), [`3ca833d`](https://github.com/mastra-ai/mastra/commit/3ca833dc994c38e3c9b4f9b4478a61cd8e07b32a), [`1edb8d1`](https://github.com/mastra-ai/mastra/commit/1edb8d1cfb963e72a12412990fb9170936c9904c), [`fbf6e32`](https://github.com/mastra-ai/mastra/commit/fbf6e324946332d0f5ed8930bf9d4d4479cefd7a), [`4753027`](https://github.com/mastra-ai/mastra/commit/4753027ee889288775c6958bdfeda03ff909af67)]:
-  - @mastra/core@0.20.0-alpha.0
-
-... 3043 more lines hidden. See full changelog in package directory.
+... 3056 more lines hidden. See full changelog in package directory.

package/.docs/organized/changelogs/%40mastra%2Fcore.md

@@ -1,5 +1,13 @@
 # @mastra/core
 
+## 0.24.7-alpha.2
+
+### Patch Changes
+
+- Fix writer.custom not working during workflow resume operations ([#10921](https://github.com/mastra-ai/mastra/pull/10921))
+
+  When a workflow step is resumed, the writer parameter was not being properly passed through, causing writer.custom() calls to fail. This fix ensures the writableStream parameter is correctly passed to both run.resume() and run.start() calls in the workflow execution engine, allowing custom events to be emitted properly during resume operations.
+
 ## 0.24.7-alpha.1
 
 ### Patch Changes
@@ -490,13 +498,5 @@
 
   **Backend changes (@mastra/core):**
   - Add assistant messages to messageList immediately after LLM execution
-  - Flush messages synchronously before suspension to persist state
-  - Create thread if it doesn't exist before flushing
-  - Add metadata helpers to persist and remove tool approval state
-  - Pass saveQueueManager and memory context through workflow for immediate persistence
-
-  **Frontend changes (@mastra/react):**
-  - Extract runId from pending approvals to enable resumption after refresh
-  - Convert `pendingToolApprovals` (DB format) to `requireApprovalMetadata` (runtime format)
 
-... 5399 more lines hidden. See full changelog in package directory.
+... 5407 more lines hidden. See full changelog in package directory.

package/.docs/organized/changelogs/%40mastra%2Fdeployer-cloud.md

@@ -1,5 +1,13 @@
 # @mastra/deployer-cloud
 
+## 0.24.7-alpha.2
+
+### Patch Changes
+
+- Updated dependencies [[`b685c9c`](https://github.com/mastra-ai/mastra/commit/b685c9c0b89f49e0d4542c4ac72569682db69794)]:
+  - @mastra/core@0.24.7-alpha.2
+  - @mastra/deployer@0.24.7-alpha.2
+
 ## 0.24.7-alpha.1
 
 ### Patch Changes
@@ -491,12 +499,4 @@
 
 ### Patch Changes
 
-- Updated dependencies [[`4a70ccc`](https://github.com/mastra-ai/mastra/commit/4a70ccc5cfa12ae9c2b36545a5814cd98e5a0ead)]:
-  - @mastra/core@0.19.1-alpha.1
-  - @mastra/deployer@0.19.1-alpha.1
-
-## 0.19.1-alpha.0
-
-### Patch Changes
-
-... 579 more lines hidden. See full changelog in package directory.
+... 587 more lines hidden. See full changelog in package directory.

package/.docs/organized/changelogs/%40mastra%2Fdeployer.md

@@ -1,5 +1,13 @@
 # @mastra/deployer
 
+## 0.24.7-alpha.2
+
+### Patch Changes
+
+- Updated dependencies [[`b685c9c`](https://github.com/mastra-ai/mastra/commit/b685c9c0b89f49e0d4542c4ac72569682db69794)]:
+  - @mastra/core@0.24.7-alpha.2
+  - @mastra/server@0.24.7-alpha.2
+
 ## 0.24.7-alpha.1
 
 ### Patch Changes
@@ -491,12 +499,4 @@
 
 ## 0.21.0-alpha.1
 
-### Patch Changes
-
-- Add typescript to global externals to reduce bundling OOM ([#8789](https://github.com/mastra-ai/mastra/pull/8789))
-
-- Improve error handling formatting in dev/build bundling. ([#8792](https://github.com/mastra-ai/mastra/pull/8792))
-
-- Remove validation step in bundling process ([#8778](https://github.com/mastra-ai/mastra/pull/8778))
-
-... 4946 more lines hidden. See full changelog in package directory.
+... 4954 more lines hidden. See full changelog in package directory.

package/.docs/organized/changelogs/%40mastra%2Fmcp-docs-server.md

@@ -1,5 +1,13 @@
 # @mastra/mcp-docs-server
 
+## 0.13.46-alpha.2
+
+### Patch Changes
+
+- Updated dependencies [[`6c38116`](https://github.com/mastra-ai/mastra/commit/6c381162fc107bfe1271284a90a507d9e3304241), [`b685c9c`](https://github.com/mastra-ai/mastra/commit/b685c9c0b89f49e0d4542c4ac72569682db69794)]:
+  - @mastra/mcp@0.14.5-alpha.0
+  - @mastra/core@0.24.7-alpha.2
+
 ## 0.13.46-alpha.1
 
 ### Patch Changes
@@ -491,12 +499,4 @@
   - @mastra/core@0.17.0
   - @mastra/mcp@0.13.0
 
-## 0.13.22-alpha.8
-
-### Patch Changes
-
-- Updated dependencies [[`05c7abf`](https://github.com/mastra-ai/mastra/commit/05c7abfe105a015b7760c9bf33ff4419727502a0), [`aee4f00`](https://github.com/mastra-ai/mastra/commit/aee4f00e61e1a42e81a6d74ff149dbe69e32695a)]:
-  - @mastra/core@0.17.0-alpha.8
-
-
-... 2087 more lines hidden. See full changelog in package directory.
+... 2095 more lines hidden. See full changelog in package directory.

package/.docs/organized/changelogs/%40mastra%2Fmcp.md

@@ -1,5 +1,14 @@
 # @mastra/mcp
 
+## 0.14.5-alpha.0
+
+### Patch Changes
+
+- add flag to skip sessions and streaming in serverless mcp ([#10927](https://github.com/mastra-ai/mastra/pull/10927))
+
+- Updated dependencies [[`b685c9c`](https://github.com/mastra-ai/mastra/commit/b685c9c0b89f49e0d4542c4ac72569682db69794)]:
+  - @mastra/core@0.24.7-alpha.2
+
 ## 0.14.4
 
 ### Patch Changes
@@ -489,14 +498,5 @@
 - e1aed55: Fixed an issue where keep-alive messages were interfering with endpoint messages on initial SSE connection
 - 03997ae: Update peerdeps
 - Updated dependencies [227c7e6]
-- Updated dependencies [12cae67]
-- Updated dependencies [fd3a3eb]
-- Updated dependencies [6faaee5]
-- Updated dependencies [4232b14]
-- Updated dependencies [a89de7e]
-- Updated dependencies [5a37d0c]
-- Updated dependencies [4bde0cb]
-- Updated dependencies [cf4f357]
-- Updated dependencies [ad888a2]
-
-... 2354 more lines hidden. See full changelog in package directory.
+
+... 2363 more lines hidden. See full changelog in package directory.

package/.docs/organized/changelogs/%40mastra%2Fplayground-ui.md

@@ -1,5 +1,14 @@
 # @mastra/playground-ui
 
+## 7.0.0-alpha.2
+
+### Patch Changes
+
+- Updated dependencies [[`461f5f7`](https://github.com/mastra-ai/mastra/commit/461f5f747ce07d77dc048cf0f5df44744183c3c3), [`b685c9c`](https://github.com/mastra-ai/mastra/commit/b685c9c0b89f49e0d4542c4ac72569682db69794)]:
+  - @mastra/client-js@0.17.0-alpha.2
+  - @mastra/core@0.24.7-alpha.2
+  - @mastra/react@0.0.22-alpha.2
+
 ## 7.0.0-alpha.1
 
 ### Patch Changes
@@ -489,14 +498,5 @@
 
 - Add div wrapper around entity tables to fix table vertical position ([#8758](https://github.com/mastra-ai/mastra/pull/8758))
 
-- Update peer dependencies to match core package version bump (0.21.0) ([#8557](https://github.com/mastra-ai/mastra/pull/8557))
-
-- handle error case in react sdk ([#8676](https://github.com/mastra-ai/mastra/pull/8676))
-
-- Make sure to convert the agent instructions when showing them ([#8702](https://github.com/mastra-ai/mastra/pull/8702))
-
-- Update peer dependencies to match core package version bump (0.21.0) ([#8626](https://github.com/mastra-ai/mastra/pull/8626))
-
-- Customize AITraces type to seamlessly work on Cloud too ([#8759](https://github.com/mastra-ai/mastra/pull/8759))
 
-... 3949 more lines hidden. See full changelog in package directory.
+... 3958 more lines hidden. See full changelog in package directory.

package/.docs/organized/changelogs/%40mastra%2Freact.md

@@ -1,5 +1,12 @@
 # @mastra/react-hooks
 
+## 0.0.22-alpha.2
+
+### Patch Changes
+
+- Updated dependencies [[`461f5f7`](https://github.com/mastra-ai/mastra/commit/461f5f747ce07d77dc048cf0f5df44744183c3c3)]:
+  - @mastra/client-js@0.17.0-alpha.2
+
 ## 0.0.22-alpha.1
 
 ### Patch Changes
@@ -491,12 +498,5 @@
 
 ## 0.0.2-alpha.1
 
-### Patch Changes
-
-- Updated dependencies []:
-  - @mastra/client-js@0.14.1-alpha.1
-
-## 0.0.2-alpha.0
-
 
-... 30 more lines hidden. See full changelog in package directory.
+... 37 more lines hidden. See full changelog in package directory.

package/.docs/organized/changelogs/%40mastra%2Fserver.md

@@ -1,5 +1,12 @@
 # @mastra/server
 
+## 0.24.7-alpha.2
+
+### Patch Changes
+
+- Updated dependencies [[`b685c9c`](https://github.com/mastra-ai/mastra/commit/b685c9c0b89f49e0d4542c4ac72569682db69794)]:
+  - @mastra/core@0.24.7-alpha.2
+
 ## 0.24.7-alpha.1
 
 ### Patch Changes
@@ -492,11 +499,4 @@
 
 ### Patch Changes
 
-- Fix TypeScript errors with provider-defined tools by updating ai-v5 and openai-v5 to matching provider-utils versions. This ensures npm deduplicates to a single provider-utils instance, resolving type incompatibility issues when passing provider tools to Agent. ([#8584](https://github.com/mastra-ai/mastra/pull/8584))
-
-  Also adds deprecation warning to Agent import from root path to encourage using the recommended subpath import.
-
-- Updated dependencies [[`a6d69c5`](https://github.com/mastra-ai/mastra/commit/a6d69c5fb50c0875b46275811fece5862f03c6a0), [`84199af`](https://github.com/mastra-ai/mastra/commit/84199af8673f6f9cb59286ffb5477a41932775de), [`7f431af`](https://github.com/mastra-ai/mastra/commit/7f431afd586b7d3265075e73106eb73167edbb86)]:
-  - @mastra/core@0.20.1-alpha.3
-
-... 3913 more lines hidden. See full changelog in package directory.
+... 3920 more lines hidden. See full changelog in package directory.

package/.docs/raw/agents/overview.mdx

@@ -355,9 +355,9 @@ const response = await testAgent.generate(
 console.log(response.object);
 ```
 
-### With Tool Calling
+### Structuring sub agent
 
-Use the `model` property to ensure that your agent can execute multi-step LLM calls with tool calling.
+Use the `model` property to have a separate agent generate the structured output for you.
 
 ```typescript showLineNumbers copy
 import { z } from "zod";
@@ -420,6 +420,21 @@ const response = await testAgentThatDoesntSupportStructuredOutput.generate(
 console.log(response.object);
 ```
 
+:::info[Gemini 2.5 with tools]
+
+Gemini 2.5 models do not support combining `response_format` (structured output) with function calling (tools) in the same API call. If your agent has tools and you're using `structuredOutput` with a Gemini 2.5 model, you must set `jsonPromptInjection: true` to avoid the error `Function calling with a response mime type: 'application/json' is unsupported`.
+
+```typescript
+const response = await agentWithTools.generate("Your prompt", {
+  structuredOutput: {
+    schema: yourSchema,
+    jsonPromptInjection: true, // Required for Gemini 2.5 when tools are present
+  },
+});
+```
+
+:::
+
 ## Using tools
 
 Agents can use tools to go beyond language generation, enabling structured interactions with external APIs and services. Tools allow agents to access data and perform clearly defined operations in a reliable, repeatable way.

package/.docs/raw/mcp/overview.mdx

@@ -99,6 +99,12 @@ export const testMcpServer = new MCPServer({
 
 > See [MCPServer](/reference/tools/mcp-server) for a full list of configuration options.
 
+### Serverless deployments
+
+`MCPServer` can be deployed in serverless environments (Cloudflare Workers, Vercel Edge Functions, AWS Lambda, etc.) by enabling the `serverless: true` option in `startHTTP()`. This runs the server in stateless mode, where each request is handled independently without session management.
+
+**Note:** Some MCP features require persistent connections and won't work in serverless mode, including elicitation, resource subscriptions, and update notifications. See the [serverless section](/reference/tools/mcp-server#starthttp) in the API reference for full details and limitations.
+
 ## Registering an `MCPServer`
 
 To make an MCP server available to other systems or agents that support the protocol, register it in the main `Mastra` instance using `mcpServers`.

package/.docs/raw/reference/tools/mcp-server.mdx

@@ -387,7 +387,7 @@ const httpServer = http.createServer(async (req, res) => {
     req,
     res,
     options: {
-      sessionIdGenerator: undefined,
+      sessionIdGenerator: () => randomUUID(),
     },
   });
 });
@@ -397,6 +397,70 @@ httpServer.listen(PORT, () => {
 });
 ```
 
+For **serverless environments** (Supabase Edge Functions, Cloudflare Workers, Vercel Edge, etc.), use `serverless: true` to enable stateless operation:
+
+```typescript
+// Supabase Edge Function example
+import { serve } from "https://deno.land/std@0.168.0/http/server.ts";
+import { MCPServer } from "@mastra/mcp";
+// Note: You will need to convert req/res format from Deno to Node
+import { toReqRes, toFetchResponse } from "fetch-to-node";
+
+const server = new MCPServer({
+  name: "my-serverless-mcp",
+  version: "1.0.0",
+  tools: { /* your tools */ },
+});
+
+serve(async (req) => {
+  const url = new URL(req.url);
+  
+  if (url.pathname === "/mcp") {
+    // Convert Deno Request to Node.js-compatible format
+    const { req: nodeReq, res: nodeRes } = toReqRes(req);
+    
+    await server.startHTTP({
+      url,
+      httpPath: "/mcp",
+      req: nodeReq,
+      res: nodeRes,
+      options: {
+        serverless: true, // ← Enable stateless mode for serverless
+      },
+    });
+    
+    return toFetchResponse(nodeRes);
+  }
+  
+  return new Response("Not found", { status: 404 });
+});
+```
+
+> **When to use `serverless: true`**
+>
+> Use `serverless: true` when deploying to environments where each request runs in a fresh, stateless execution context:
+> - Supabase Edge Functions
+> - Cloudflare Workers
+> - Vercel Edge Functions
+> - Netlify Edge Functions
+> - AWS Lambda
+> - Deno Deploy
+>
+> Use the default session-based mode (without `serverless: true`) for:
+> - Long-lived Node.js servers
+> - Docker containers
+> - Traditional hosting (VPS, dedicated servers)
+>
+> The serverless mode disables session management and creates fresh server instances per request, which is necessary for stateless environments where memory doesn't persist between invocations.
+>
+> **Note:** The following MCP features require session state or persistent connections and will **not work** in serverless mode:
+> - **Elicitation** - Interactive user input requests during tool execution require session management to route responses back to the correct client
+> - **Resource subscriptions** - `resources/subscribe` and `resources/unsubscribe` need persistent connections to maintain subscription state
+> - **Resource update notifications** - `resources.notifyUpdated()` requires active subscriptions and persistent connections to notify clients
+> - **Prompt list change notifications** - `prompts.notifyListChanged()` requires persistent connections to push updates to clients
+>
+> These features work normally in long-lived server environments (Node.js servers, Docker containers, etc.).
+
 Here are the details for the values needed by the `startHTTP` method:
 
 <PropertiesTable
@@ -437,6 +501,13 @@ The `StreamableHTTPServerTransportOptions` object allows you to customize the be
 
 <PropertiesTable
   content={[
+    {
+      name: "serverless",
+      type: "boolean",
+      description:
+        "If `true`, runs in stateless mode without session management. Each request is handled independently with a fresh server instance. Essential for serverless environments (Cloudflare Workers, Supabase Edge Functions, Vercel Edge, etc.) where sessions cannot persist between invocations. Defaults to `false`.",
+      optional: true,
+    },
     {
       name: "sessionIdGenerator",
       type: "(() => string) | undefined",

package/CHANGELOG.md

@@ -1,5 +1,13 @@
 # @mastra/mcp-docs-server
 
+## 0.13.46-alpha.2
+
+### Patch Changes
+
+- Updated dependencies [[`6c38116`](https://github.com/mastra-ai/mastra/commit/6c381162fc107bfe1271284a90a507d9e3304241), [`b685c9c`](https://github.com/mastra-ai/mastra/commit/b685c9c0b89f49e0d4542c4ac72569682db69794)]:
+  - @mastra/mcp@0.14.5-alpha.0
+  - @mastra/core@0.24.7-alpha.2
+
 ## 0.13.46-alpha.1
 
 ### Patch Changes

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mastra/mcp-docs-server",
-  "version": "0.13.46-alpha.1",
+  "version": "0.13.46-alpha.2",
   "description": "MCP server for accessing Mastra.ai documentation, changelogs, and news.",
   "type": "module",
   "main": "dist/index.js",
@@ -33,8 +33,8 @@
     "uuid": "^11.1.0",
     "zod": "^3.25.76",
     "zod-to-json-schema": "^3.24.6",
-    "@mastra/core": "0.24.7-alpha.1",
-    "@mastra/mcp": "^0.14.4"
+    "@mastra/core": "0.24.7-alpha.2",
+    "@mastra/mcp": "^0.14.5-alpha.0"
   },
   "devDependencies": {
     "@hono/node-server": "^1.19.5",
@@ -50,7 +50,7 @@
     "typescript": "^5.8.3",
     "vitest": "^3.2.4",
     "@internal/lint": "0.0.64",
-    "@mastra/core": "0.24.7-alpha.1"
+    "@mastra/core": "0.24.7-alpha.2"
   },
   "homepage": "https://mastra.ai",
   "repository": {