@mastra/mcp-docs-server 0.13.28 → 0.13.29-alpha.0

package/.docs/organized/changelogs/mastra.md

@@ -1,5 +1,61 @@
 # mastra
 
+## 0.15.1-alpha.0
+
+### Patch Changes
+
+- Improve the overall flow of the `create-mastra` CLI by first asking all questions and then creating the project structure. If you skip entering an API key during the wizard, the `your-api-key` placeholder will now be added to an `.env.example` file instead of `.env`. ([#8603](https://github.com/mastra-ai/mastra/pull/8603))
+
+- Updated dependencies [[`0d71771`](https://github.com/mastra-ai/mastra/commit/0d71771f5711164c79f8e80919bc84d6bffeb6bc), [`0d6e55e`](https://github.com/mastra-ai/mastra/commit/0d6e55ecc5a2e689cd4fc9c86525e0eb54d82372)]:
+  - @mastra/core@0.20.2-alpha.0
+  - @mastra/deployer@0.20.2-alpha.0
+
+## 0.15.0
+
+### Minor Changes
+
+- Update peer dependencies to match core package version bump (0.20.1) ([#8589](https://github.com/mastra-ai/mastra/pull/8589))
+
+### Patch Changes
+
+- workflow run thread more visible ([#8539](https://github.com/mastra-ai/mastra/pull/8539))
+
+- Mutable shared workflow run state ([#8545](https://github.com/mastra-ai/mastra/pull/8545))
+
+- streamLegacy/generateLegacy clarification in playground ([#8468](https://github.com/mastra-ai/mastra/pull/8468))
+
+- avoid refetching memory threads and messages on window focus ([#8519](https://github.com/mastra-ai/mastra/pull/8519))
+
+- add tripwire reason in playground ([#8568](https://github.com/mastra-ai/mastra/pull/8568))
+
+- Save waiting step status in snapshot ([#8576](https://github.com/mastra-ai/mastra/pull/8576))
+
+- Added AI SDK provider packages to model router for anthropic/google/openai/openrouter/xai ([#8559](https://github.com/mastra-ai/mastra/pull/8559))
+
+- Convert WorkflowWatchResult to WorkflowResult in workflow graph ([#8541](https://github.com/mastra-ai/mastra/pull/8541))
+
+- add new deploy to cloud button ([#8549](https://github.com/mastra-ai/mastra/pull/8549))
+
+- remove icons in entity lists ([#8520](https://github.com/mastra-ai/mastra/pull/8520))
+
+- add client search to all entities ([#8523](https://github.com/mastra-ai/mastra/pull/8523))
+
+- Fixed an issue where model router was adding /chat/completions to API urls when it shouldn't. ([#8589](https://github.com/mastra-ai/mastra/pull/8589))
+  fixed an issue with provider ID rendering in playground UI
+
+- Fix useStreamWorkflow unmounting breaking stream call ([#8449](https://github.com/mastra-ai/mastra/pull/8449))
+
+- Remove shell from dev ([#8466](https://github.com/mastra-ai/mastra/pull/8466))
+
+- UX for the agents page ([#8517](https://github.com/mastra-ai/mastra/pull/8517))
+
+- add icons into playground titles + a link to the entity doc ([#8518](https://github.com/mastra-ai/mastra/pull/8518))
+
+- Updated dependencies [[`c621613`](https://github.com/mastra-ai/mastra/commit/c621613069173c69eb2c3ef19a5308894c6549f0), [`ee17cec`](https://github.com/mastra-ai/mastra/commit/ee17cec065f4454740c9cc8f8a841027a5990f57), [`12b1189`](https://github.com/mastra-ai/mastra/commit/12b118942445e4de0dd916c593e33ec78dc3bc73), [`42ffed3`](https://github.com/mastra-ai/mastra/commit/42ffed311b9d8750652bbc55c773be62c989fcc6), [`4783b30`](https://github.com/mastra-ai/mastra/commit/4783b3063efea887825514b783ba27f67912c26d), [`076b092`](https://github.com/mastra-ai/mastra/commit/076b0924902ff0f49d5712d2df24c4cca683713f), [`2aee9e7`](https://github.com/mastra-ai/mastra/commit/2aee9e7d188b8b256a4ddc203ccefb366b4867fa), [`c582906`](https://github.com/mastra-ai/mastra/commit/c5829065a346260f96c4beb8af131b94804ae3ad), [`fa2eb96`](https://github.com/mastra-ai/mastra/commit/fa2eb96af16c7d433891a73932764960d3235c1d), [`ee9108f`](https://github.com/mastra-ai/mastra/commit/ee9108fa29bb8368fc23df158c9f0645b2d7b65c), [`4783b30`](https://github.com/mastra-ai/mastra/commit/4783b3063efea887825514b783ba27f67912c26d), [`a739d0c`](https://github.com/mastra-ai/mastra/commit/a739d0c8b37cd89569e04a6ca0827083c6167e19), [`a9c4cb7`](https://github.com/mastra-ai/mastra/commit/a9c4cb7d6a35de23ca51066f166a66e0e4cca418), [`603e927`](https://github.com/mastra-ai/mastra/commit/603e9279db8bf8a46caf83881c6b7389ccffff7e), [`cd45982`](https://github.com/mastra-ai/mastra/commit/cd4598291cda128a88738734ae6cbef076ebdebd), [`874f74d`](https://github.com/mastra-ai/mastra/commit/874f74da4b1acf6517f18132d035612c3ecc394a), [`b728a45`](https://github.com/mastra-ai/mastra/commit/b728a45ab3dba59da0f5ee36b81fe246659f305d), [`0baf2ba`](https://github.com/mastra-ai/mastra/commit/0baf2bab8420277072ef1f95df5ea7b0a2f61fe7), [`10e633a`](https://github.com/mastra-ai/mastra/commit/10e633a07d333466d9734c97acfc3dbf757ad2d0), [`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), [`26e968d`](https://github.com/mastra-ai/mastra/commit/26e968db2171ded9e4d47aa1b4f19e1e771158d0), [`cbd3fb6`](https://github.com/mastra-ai/mastra/commit/cbd3fb65adb03a7c0df193cb998aed5ac56675ee)]:
+  - @mastra/core@0.20.1
+  - @mastra/deployer@0.20.1
+  - @mastra/mcp@0.13.4
+
 ## 0.15.0-alpha.3
 
 ### Minor Changes
@@ -243,60 +299,4 @@
 
 ### Patch Changes
 
-- Update peer deps ([#8154](https://github.com/mastra-ai/mastra/pull/8154))
-
-- Fixed an issue in playground where text-start/end parts were ignored in handleStreamChunk and tool ordering vs text wasn't retained ([#8234](https://github.com/mastra-ai/mastra/pull/8234))
-
-- Add conditional chaining to scorer.agentNames return ([#8199](https://github.com/mastra-ai/mastra/pull/8199))
-
-- Show model that worked when there are model fallbacks ([#8167](https://github.com/mastra-ai/mastra/pull/8167))
-
-- Updated dependencies [[`5089c84`](https://github.com/mastra-ai/mastra/commit/5089c84a2f535ad12e79b5aa524ad7d8ca5e2b4c), [`5f4e677`](https://github.com/mastra-ai/mastra/commit/5f4e67757bc23f2694d83af10f88cfccdc6013ff), [`5c98f03`](https://github.com/mastra-ai/mastra/commit/5c98f03ae76d9a93cd6be206b4abb7bf186b3163), [`57b75b0`](https://github.com/mastra-ai/mastra/commit/57b75b01c0c64d91c50d7384c700afda89456fe8), [`4c5e65d`](https://github.com/mastra-ai/mastra/commit/4c5e65de746fbdab23eb6072cb999f4c7aeef9f3), [`504438b`](https://github.com/mastra-ai/mastra/commit/504438b961bde211071186bba63a842c4e3db879), [`57b6dd5`](https://github.com/mastra-ai/mastra/commit/57b6dd50f9e6d92c0ed3e7199e6a92752025e3a1), [`a7243e2`](https://github.com/mastra-ai/mastra/commit/a7243e2e58762667a6e3921e755e89d6bb0a3282), [`504438b`](https://github.com/mastra-ai/mastra/commit/504438b961bde211071186bba63a842c4e3db879), [`7fceb0a`](https://github.com/mastra-ai/mastra/commit/7fceb0a327d678e812f90f5387c5bc4f38bd039e), [`df64f9e`](https://github.com/mastra-ai/mastra/commit/df64f9ef814916fff9baedd861c988084e7c41de), [`809eea0`](https://github.com/mastra-ai/mastra/commit/809eea092fa80c3f69b9eaf078d843b57fd2a88e), [`683e5a1`](https://github.com/mastra-ai/mastra/commit/683e5a1466e48b686825b2c11f84680f296138e4), [`3679378`](https://github.com/mastra-ai/mastra/commit/3679378673350aa314741dc826f837b1984149bc), [`7775bc2`](https://github.com/mastra-ai/mastra/commit/7775bc20bb1ad1ab24797fb420e4f96c65b0d8ec), [`db1891a`](https://github.com/mastra-ai/mastra/commit/db1891a4707443720b7cd8a260dc7e1d49b3609c), [`e8f379d`](https://github.com/mastra-ai/mastra/commit/e8f379d390efa264c4e0874f9ac0cf8839b07777), [`652066b`](https://github.com/mastra-ai/mastra/commit/652066bd1efc6bb6813ba950ed1d7573e8b7d9d4), [`ea8d386`](https://github.com/mastra-ai/mastra/commit/ea8d386cd8c5593664515fd5770c06bf2aa980ef), [`c2a4919`](https://github.com/mastra-ai/mastra/commit/c2a4919ba6797d8bdb1509e02287496eef69303e), [`6f67656`](https://github.com/mastra-ai/mastra/commit/6f676562276926e2982401574d1e07157579be30), [`0130986`](https://github.com/mastra-ai/mastra/commit/0130986fc62d0edcc626dd593282661dbb9af141), [`5dc8e9a`](https://github.com/mastra-ai/mastra/commit/5dc8e9a7f8472298cd3d4e8a0cf6d265529f287d)]:
-  - @mastra/deployer@0.19.0-alpha.1
-  - @mastra/mcp@0.13.2-alpha.0
-  - @mastra/core@0.19.0-alpha.1
-  - @mastra/loggers@0.10.14-alpha.0
-
-## 0.13.3-alpha.0
-
-### Patch Changes
-
-- Remove legacy helpers ([#8017](https://github.com/mastra-ai/mastra/pull/8017))
-
-- add a way to hide the deploy mastra cloud button ([#8137](https://github.com/mastra-ai/mastra/pull/8137))
-
-- Add types in the streamVNext codepath, fixes for various issues across multiple packages surfaced from type issues, align return types. ([#8010](https://github.com/mastra-ai/mastra/pull/8010))
-
-- Add model fallbacks to playground ([#7427](https://github.com/mastra-ai/mastra/pull/7427))
-
-- Updated dependencies [[`dc099b4`](https://github.com/mastra-ai/mastra/commit/dc099b40fb31147ba3f362f98d991892033c4c67), [`b342a68`](https://github.com/mastra-ai/mastra/commit/b342a68e1399cf1ece9ba11bda112db89d21118c), [`303a9c0`](https://github.com/mastra-ai/mastra/commit/303a9c0d7dd58795915979f06a0512359e4532fb), [`370f8a6`](https://github.com/mastra-ai/mastra/commit/370f8a6480faec70fef18d72e5f7538f27004301), [`623ffaf`](https://github.com/mastra-ai/mastra/commit/623ffaf2d969e11e99a0224633cf7b5a0815c857), [`9fc1613`](https://github.com/mastra-ai/mastra/commit/9fc16136400186648880fd990119ac15f7c02ee4), [`61f62aa`](https://github.com/mastra-ai/mastra/commit/61f62aa31bc88fe4ddf8da6240dbcfbeb07358bd), [`3e292ba`](https://github.com/mastra-ai/mastra/commit/3e292ba00837886d5d68a34cbc0d9b703c991883), [`418c136`](https://github.com/mastra-ai/mastra/commit/418c1366843d88e491bca3f87763899ce855ca29), [`c84b7d0`](https://github.com/mastra-ai/mastra/commit/c84b7d093c4657772140cbfd2b15ef72f3315ed5)]:
-  - @mastra/core@0.18.1-alpha.0
-  - @mastra/deployer@0.18.1-alpha.0
-
-## 0.13.2
-
-### Patch Changes
-
-- feat: implement trace scoring with batch processing capabilities ([#8033](https://github.com/mastra-ai/mastra/pull/8033))
-
-- Add model fallback handlers and apis ([#7378](https://github.com/mastra-ai/mastra/pull/7378))
-
-- dependencies updates: ([#8007](https://github.com/mastra-ai/mastra/pull/8007))
-  - Updated dependency [`fs-extra@^11.3.2` ↗︎](https://www.npmjs.com/package/fs-extra/v/11.3.2) (from `^11.3.1`, in `dependencies`)
-
-- show the tool-output stream in the playground for streamVNext ([#7983](https://github.com/mastra-ai/mastra/pull/7983))
-
-- Get rid off swr one for all ([#7931](https://github.com/mastra-ai/mastra/pull/7931))
-
-- Fix DateTimePicker style issue ([#8106](https://github.com/mastra-ai/mastra/pull/8106))
-
-- Fix navigating between scores and entity types ([#8129](https://github.com/mastra-ai/mastra/pull/8129))
-
-- Fix getting tool link path from agent in playground ui tools page ([#8135](https://github.com/mastra-ai/mastra/pull/8135))
-
-- Update Peerdeps for packages based on core minor bump ([#8025](https://github.com/mastra-ai/mastra/pull/8025))
-
-- Updated dependencies [[`288745a`](https://github.com/mastra-ai/mastra/commit/288745a19aa9557db3ab3c877d667ff59f14d79c), [`cf34503`](https://github.com/mastra-ai/mastra/commit/cf345031de4e157f29087946449e60b965e9c8a9), [`6b4b1e4`](https://github.com/mastra-ai/mastra/commit/6b4b1e4235428d39e51cbda9832704c0ba70ab32), [`3469fca`](https://github.com/mastra-ai/mastra/commit/3469fca7bb7e5e19369ff9f7044716a5e4b02585), [`a61f23f`](https://github.com/mastra-ai/mastra/commit/a61f23fbbca4b88b763d94f1d784c47895ed72d7), [`4b339b8`](https://github.com/mastra-ai/mastra/commit/4b339b8141c20d6a6d80583c7e8c5c05d8c19492), [`8f56160`](https://github.com/mastra-ai/mastra/commit/8f56160fd45c740076529148b9c225f6842d43b0), [`d1dc606`](https://github.com/mastra-ai/mastra/commit/d1dc6067b0557a71190b68d56ee15b48c26d2411), [`2d29ad9`](https://github.com/mastra-ai/mastra/commit/2d29ad92763cac02fc1d80c221ac93c39c0c5caf), [`c45298a`](https://github.com/mastra-ai/mastra/commit/c45298a0a0791db35cf79f1199d77004da0704cb), [`c4a8204`](https://github.com/mastra-ai/mastra/commit/c4a82046bfd241d6044e234bc5917d5a01fe6b55), [`d3bd4d4`](https://github.com/mastra-ai/mastra/commit/d3bd4d482a685bbb67bfa89be91c90dca3fa71ad), [`c591dfc`](https://github.com/mastra-ai/mastra/commit/c591dfc1e600fae1dedffe239357d250e146378f), [`1920c5c`](https://github.com/mastra-ai/mastra/commit/1920c5c6d666f687785c73021196aa551e579e0d), [`b6a3b65`](https://github.com/mastra-ai/mastra/commit/b6a3b65d830fa0ca7754ad6481661d1f2c878f21), [`af3abb6`](https://github.com/mastra-ai/mastra/commit/af3abb6f7c7585d856e22d27f4e7d2ece2186b9a), [`5b1ee71`](https://github.com/mastra-ai/mastra/commit/5b1ee71dc3ac92383226dc1e375642ca5f9b4224), [`282379f`](https://github.com/mastra-ai/mastra/commit/282379fafed80c6417fe1e791087110decd481ca)]:
-  - @mastra/deployer@0.18.0
-
-... 6022 more lines hidden. See full changelog in package directory.
+... 6078 more lines hidden. See full changelog in package directory.

package/.docs/organized/code-examples/heads-up-game.md

@@ -7,15 +7,15 @@
   },
   "dependencies": {
     "@ai-sdk/openai": "^1.3.23",
-    "@mastra/core": "^0.20.0",
+    "@mastra/core": "^0.20.1",
     "@mastra/libsql": "^0.15.1",
     "@mastra/loggers": "^0.10.15",
-    "@mastra/memory": "^0.15.5",
+    "@mastra/memory": "^0.15.6",
     "zod": "^3.25.76"
   },
   "devDependencies": {
     "@types/node": "^24.3.0",
-    "mastra": "^0.14.1",
+    "mastra": "^0.15.0",
     "typescript": "^5.9.2"
   }
 }

package/.docs/raw/agents/runtime-context.mdx

@@ -5,129 +5,99 @@ description: Learn how to use Mastra's RuntimeContext to provide dynamic, reques
 
 # Runtime Context
 
-Mastra provides `RuntimeContext`, a dependency injection system that lets you configure agents with runtime variables. If you find yourself creating multiple agents that perform similar tasks, runtime context allows you to consolidate them into a single, more flexible agent.
+Agents use `RuntimeContext` to access request-specific values sent alongside user messages. These values let a single agent change its behavior, functionality, model, tools, or memory usage based on the needs of each request.
 
-## Overview
+![Agents Runtime Context](/image/agents/agents-runtime-context.jpg)
 
-The dependency injection system allows you to:
+## When to use `RuntimeContext`
 
-1. Pass runtime configuration variables to agents through a type-safe `runtimeContext`
-2. Access these variables within tool execution contexts
-3. Modify agent behavior without changing the underlying code
-4. Share configuration across multiple tools within the same agent
+Use `RuntimeContext` when an agent's behavior should change based on the request or environment. For example, you might switch models or storage providers based on user details, or adjust instructions or tool selection based on the user's language.
 
-## Using `runtimeContext` with agents
+## Configuring agents with `RuntimeContext`
 
-Agents can access `runtimeContext` via the `instructions` parameter, and retrieve variables using `runtimeContext.get()`. This allows agent behavior to adapt dynamically based on user input or external configuration, without changing the underlying implementation.
+You can access the `runtimeContext` argument from any of the agent’s supported parameters. These functions can be sync or `async`, allowing you to use context values to fetch data, apply logic, or adjust behavior at runtime.
 
-```typescript {7-8,15} filename="src/mastra/agents/test-weather-agent.ts" showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
-import { Agent } from "@mastra/core/agent";
-import { testWeatherTool } from "../tools/test-weather-tool";
-
-export const testWeatherAgent = new Agent({
-  name: "test-weather-agent",
+```typescript {3,6,9,12} filename="src/dynamic-agent.ts" showLineNumbers copy
+export const dynamicAgent = new Agent({
+  name: "dynamic-agent",
   instructions: async ({ runtimeContext }) => {
-    const temperatureUnit = runtimeContext.get("temperature-unit");
-
-    return `You are a weather assistant that provides current weather information for any city.
-
-    When a user asks for weather:
-    - Extract the city name from their request
-    - Respond with: temperature, feels-like temperature, humidity, wind speed, and conditions
-    - Use ${temperatureUnit} for all temperature values
-    - If no city is mentioned, ask for a city name
-    `;
+    // ...
+  },
+  model: ({ runtimeContext }) => {
+    // ...
+  },
+  tools: ({ runtimeContext }) => {
+    // ...
+  },
+  memory: ({ runtimeContext }) => {
+    // ...
   },
-  model: openai("gpt-4o-mini"),
-  tools: { testWeatherTool }
 });
 ```
 
-### Example tool
+You can also use `runtimeContext` with other parameters like `agents`, `workflows`, `scorers`, `inputProcessors`, and `outputProcessors`.
 
-This tool exports a `WeatherRuntimeContext` type, enabling type-safe access to runtime configuration wherever the tool’s `runtimeContext` is used. It extracts `city` from `context`, which is derived from the user message passed to `.generate()`, and uses it to query a weather service API.
+> See [Agent](../../reference/agents/agent.mdx) for a full list of configuration options.
 
-```typescript {4-6, 15} filename="src/mastra/tools/test-weather-tool.ts" showLineNumbers copy
-import { createTool } from "@mastra/core/tools";
-import { z } from "zod";
+## Setting values
 
-export type WeatherRuntimeContext = {
-  "temperature-unit": "celsius" | "fahrenheit";
-};
+To set variables in `runtimeContext`, create a new instance using `new RuntimeContext()` and call `.set()` to define the values you want to include.
 
-export const testWeatherTool = createTool({
-  id: "test-weather-tool",
-  description: "Fetches the current weather for a given city",
-  inputSchema: z.object({
-    city: z.string()
-  }),
-  execute: async ({ context, runtimeContext }) => {
-    const { city } = context;
-    const unit = runtimeContext.get("temperature-unit") as WeatherRuntimeContext["temperature-unit"];
-
-    const response = await fetch(`https://weather.service?city=${city}`);
-    const { temperature, conditions } = await response.json();
-
-    return {
-      metric: unit === "celsius" ? "°C" : "°F",
-      temperature,
-      conditions
-    };
-  }
-});
-```
+The `.set()` method takes two arguments:
 
-### Example usage
+1. **key**: The name used to identify the value.
+2. **value**: The data to associate with that key.
 
-In this example, `temperature-unit` is set using `runtimeContext.set()` to either **celsius** or **fahrenheit**, allowing the agent to respond with temperatures in the appropriate unit.
+After setting the values, pass the `runtimeContext` to `.generate()` or `.stream()` to make them available to the agent.
 
-```typescript {9, 12} filename="src/test-weather-agent.ts" showLineNumbers copy
+```typescript {8,11} filename="src/test-dynamic-agent.ts" showLineNumbers copy
 import { mastra } from "./mastra";
 import { RuntimeContext } from "@mastra/core/runtime-context";
-import { WeatherRuntimeContext } from "./mastra/tools/test-weather-tool";
+import { UserTier } from "./mastra/agents/dynamic-agent"
 
-const agent = mastra.getAgent("testWeatherAgent");
+const agent = mastra.getAgent("dynamicAgent");
 
-const runtimeContext = new RuntimeContext<WeatherRuntimeContext>();
+const runtimeContext = new RuntimeContext<UserTier>();
+runtimeContext.set("user-tier", "enterprise");
 
-runtimeContext.set("temperature-unit", "celsius");
-
-const response = await agent.generate("What's the weather in London?", {
+const response = await agent.generate("Help plan my day.", {
   runtimeContext
 });
-
-console.log(response.text);
 ```
 
-## Accessing `runtimeContext` with server middleware
+## Accessing values
 
-You can populate `runtimeContext` dynamically in server middleware by extracting information from the request. In this example, the `temperature-unit` is set based on the Cloudflare `CF-IPCountry` header to ensure responses match the user's locale.
+The example below accesses a `user-tier` value from `runtimeContext` to determine which model and instructions to use. The context is typed to provide safety and autocomplete when working with `.get()` and `.set()`.
 
-```typescript {2,4,9-18} filename="src/mastra/index.ts" showLineNumbers copy
-import { Mastra } from "@mastra/core/mastra";
+```typescript {12,19} filename="src/mastra/agents/dynamic-agent.ts" showLineNumbers copy
+import { openai } from "@ai-sdk/openai";
+import { Agent } from "@mastra/core/agent";
 import { RuntimeContext } from "@mastra/core/runtime-context";
-import { testWeatherAgent } from "./agents/test-weather-agent";
-import { WeatherRuntimeContext } from "./mastra/tools/test-weather-tool";
-
-export const mastra = new Mastra({
-  agents: { testWeatherAgent },
-  server: {
-    middleware: [
-      async (context, next) => {
-        const country = context.req.header("CF-IPCountry");
-        const runtimeContext = context.get("runtimeContext") as RuntimeContext<WeatherRuntimeContext>;
-
-        runtimeContext.set("temperature-unit", country === "US" ? "fahrenheit" : "celsius");
-
-        await next();
-      }
-    ]
+
+export type UserTier = {
+  "user-tier": "enterprise" | "pro";
+};
+
+export const dynamicAgent = new Agent({
+  name: "dynamic-agent",
+  instructions: async ({ runtimeContext }: { runtimeContext: RuntimeContext<UserTier> }) => {
+    const userTier = runtimeContext.get("user-tier");
+
+    const result = await db.query("SELECT instructions FROM config WHERE tier = ?", [userTier]);
+
+    return result[0].instructions;
+  },
+  model: ({ runtimeContext }: { runtimeContext: RuntimeContext<UserTier> }) => {
+    const userTier = runtimeContext.get("user-tier");
+
+    return userTier === "enterprise"
+      ? openai("gpt-4o-mini")
+      : openai("gpt-4.1-nano");
   }
 });
 ```
 
 ## Related
 
-- [Dynamic Agents](./dynamic-agents.mdx)
 - [Tool Runtime Context](../tools-mcp/runtime-context.mdx)
+- [Server Middleware Runtime Context](../server-db/middleware.mdx)

package/.docs/raw/reference/workflows/workflow-methods/dountil.mdx

@@ -5,7 +5,7 @@ description: Documentation for the `Workflow.dountil()` method in workflows, whi
 
 # Workflow.dountil()
 
-The `.dountil()` method creates a loop that executes a step until a condition is met.
+The `.dountil()` method executes a step until a condition is met. It always runs the step at least once before evaluating the condition. The first time the condition is evaluated, `iterationCount` is `1`.
 
 ## Usage example
 
@@ -25,9 +25,9 @@ workflow.dountil(step1, async ({ inputData }) => true);
     },
     {
       name: "condition",
-      type: "(params : { inputData: any}) => Promise<boolean>",
+      type: "(params : ExecuteParams & { iterationCount: number }) => Promise<boolean>",
       description:
-        "A function that returns a boolean indicating whether to continue the loop",
+        "A function that returns a boolean indicating whether to continue the loop. The function receives the execution parameters and the iteration count.",
       isOptional: false,
     },
   ]}
@@ -48,3 +48,5 @@ workflow.dountil(step1, async ({ inputData }) => true);
 ## Related
 
 - [Control Flow](../../../docs/workflows/control-flow.mdx)
+
+- [ExecuteParams](../step.mdx#ExecuteParams)

package/.docs/raw/reference/workflows/workflow-methods/dowhile.mdx

@@ -5,7 +5,7 @@ description: Documentation for the `Workflow.dowhile()` method in workflows, whi
 
 # Workflow.dowhile()
 
-The `.dowhile()` method creates a loop that executes a step while a condition is met.
+The `.dowhile()` method executes a step while a condition is met. It always runs the step at least once before evaluating the condition. The first time the condition is evaluated, `iterationCount` is `1`.
 
 ## Usage example
 
@@ -25,9 +25,9 @@ workflow.dowhile(step1, async ({ inputData }) => true);
     },
     {
       name: "condition",
-      type: "(params : { inputData: any}) => Promise<boolean>",
+      type: "(params : ExecuteParams & { iterationCount: number }) => Promise<boolean>",
       description:
-        "A function that returns a boolean indicating whether to continue the loop",
+        "A function that returns a boolean indicating whether to continue the loop. The function receives the execution parameters and the iteration count.",
       isOptional: false,
     },
   ]}
@@ -48,3 +48,5 @@ workflow.dowhile(step1, async ({ inputData }) => true);
 ## Related
 
 - [Control Flow](../../../docs/workflows/control-flow.mdx)
+
+- [ExecuteParams](../step.mdx#ExecuteParams)

package/.docs/raw/server-db/middleware.mdx

@@ -138,7 +138,33 @@ be inspected by middleware to tailor behaviour:
   },
 }
 ```
-
 - `x-mastra-cloud`: request originates from Mastra Cloud
 - `x-mastra-client-type`: identifies the client SDK, e.g. `js` or `python`
 - `x-mastra-dev-playground`: request triggered from a local playground
+
+### Setting `runtimeContext`
+
+You can populate `runtimeContext` dynamically in server middleware by extracting information from the request. In this example, the `temperature-unit` is set based on the Cloudflare `CF-IPCountry` header to ensure responses match the user's locale.
+
+```typescript filename="src/mastra/index.ts" showLineNumbers copy
+import { Mastra } from "@mastra/core/mastra";
+import { RuntimeContext } from "@mastra/core/runtime-context";
+import { testWeatherAgent } from "./agents/test-weather-agent";
+import { WeatherRuntimeContext } from "./mastra/tools/test-weather-tool";
+
+export const mastra = new Mastra({
+  agents: { testWeatherAgent },
+  server: {
+    middleware: [
+      async (context, next) => {
+        const country = context.req.header("CF-IPCountry");
+        const runtimeContext = context.get("runtimeContext") as RuntimeContext<WeatherRuntimeContext>;
+
+        runtimeContext.set("temperature-unit", country === "US" ? "fahrenheit" : "celsius");
+
+        await next();
+      }
+    ]
+  }
+});
+```

package/.docs/raw/workflows/control-flow.mdx

@@ -125,6 +125,60 @@ export const testWorkflow = createWorkflow({...})
   .commit();
 ```
 
+### Loop management
+
+Loop conditions can be implemented in different ways depending on how you want the loop to end. Common patterns include checking values returned in `inputData`, setting a maximum number of iterations, or aborting execution when a limit is reached.
+
+#### Conditional loops
+
+The `inputData` for a loop step is the output of a previous step. Use the values in `inputData` to determine whether the loop should continue or stop.
+
+```typescript {7} filename="src/mastra/workflows/test-workflow.ts" showLineNumbers copy
+import { createWorkflow, createStep } from "@mastra/core/workflows";
+import { z } from "zod";
+
+const counterStep = createStep({...});
+
+export const testWorkflow = createWorkflow({...})
+.dountil(nestedWorkflowStep, async ({ inputData: { userResponse } }) => userResponse === "yes")
+.commit();
+```
+
+#### Limiting loops
+
+The `iterationCount` tracks how many times the loop step has run. You can use this to limit the number of iterations and prevent infinite loops. Combine it with `inputData` values to stop the loop after a set number of attempts.
+
+```typescript {7} filename="src/mastra/workflows/test-workflow.ts" showLineNumbers copy
+import { createWorkflow, createStep } from "@mastra/core/workflows";
+import { z } from "zod";
+
+const counterStep = createStep({...});
+
+export const testWorkflow = createWorkflow({...})
+.dountil(nestedWorkflowStep, async ({ inputData: { userResponse, iterationCount } }) => userResponse === "yes" || iterationCount >= 10)
+.commit();
+```
+
+#### Aborting loops
+
+Use `iterationCount` to limit how many times a loop runs. If the count exceeds your threshold, throw an error to fail the step and stop the workflow.
+
+```typescript {7} filename="src/mastra/workflows/test-workflow.ts" showLineNumbers copy
+import { createWorkflow, createStep } from "@mastra/core/workflows";
+import { z } from "zod";
+
+const counterStep = createStep({...});
+
+export const testWorkflow = createWorkflow({...})
+.dountil(nestedWorkflowStep, async ({ inputData: { userResponse, iterationCount } }) => {
+  if (iterationCount >= 10) {
+    throw new Error("Maximum iterations reached");
+  }
+  return userResponse === "yes";
+})
+.commit();
+```
+
 ### Repeating with `.foreach()`
 
 Sequentially executes the same step for each item from the `inputSchema`.

package/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @mastra/mcp-docs-server
 
+## 0.13.29-alpha.0
+
+### Patch Changes
+
+- Updated dependencies [[`0d71771`](https://github.com/mastra-ai/mastra/commit/0d71771f5711164c79f8e80919bc84d6bffeb6bc), [`0d6e55e`](https://github.com/mastra-ai/mastra/commit/0d6e55ecc5a2e689cd4fc9c86525e0eb54d82372)]:
+  - @mastra/core@0.20.2-alpha.0
+
 ## 0.13.28
 
 ### Patch Changes

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mastra/mcp-docs-server",
-  "version": "0.13.28",
+  "version": "0.13.29-alpha.0",
   "description": "MCP server for accessing Mastra.ai documentation, changelogs, and news.",
   "type": "module",
   "main": "dist/index.js",
@@ -33,7 +33,7 @@
     "uuid": "^11.1.0",
     "zod": "^3.25.76",
     "zod-to-json-schema": "^3.24.6",
-    "@mastra/core": "0.20.1",
+    "@mastra/core": "0.20.2-alpha.0",
     "@mastra/mcp": "^0.13.4"
   },
   "devDependencies": {
@@ -49,8 +49,8 @@
     "tsx": "^4.19.4",
     "typescript": "^5.8.3",
     "vitest": "^3.2.4",
-    "@mastra/core": "0.20.1",
-    "@internal/lint": "0.0.47"
+    "@internal/lint": "0.0.47",
+    "@mastra/core": "0.20.2-alpha.0"
   },
   "homepage": "https://mastra.ai",
   "repository": {