@mastra/mcp-docs-server 1.1.37 → 1.1.38-alpha.3

package/.docs/docs/server/auth/fga.md

@@ -87,6 +87,74 @@ permissionMapping: {
 
 If no mapping exists for a permission, the original string is passed through.
 
+Use `validatePermissions()` to validate the full set of permissions Mastra may emit at startup. Use this when a provider requires every Mastra permission to have an explicit provider permission slug.
+
+### Route policy coverage
+
+Mastra includes route-level FGA metadata for built-in resource routes, including agents, workflows, tools, MCP tools, memory threads, responses, and conversations. A route is checked when it has route-level `fga` metadata, when Mastra can derive built-in metadata for that route, or when the provider supplies metadata with `resolveRouteFGA()`.
+
+To deny protected routes that do not resolve FGA metadata, configure route policy coverage on the FGA provider:
+
+```typescript
+const fga = new MastraFGAWorkos({
+  resourceMapping: {
+    project: { fgaResourceType: 'project' },
+  },
+  permissionMapping: {
+    'projects:read': 'read',
+  },
+  requireForProtectedRoutes: true,
+  auditProtectedRoutes: 'warn',
+  validatePermissions: async permissions => {
+    // Throw if a Mastra permission is missing from permissionMapping.
+  },
+});
+```
+
+Set `auditProtectedRoutes: 'error'` to fail startup when protected routes are missing built-in FGA metadata. If `requireForProtectedRoutes` is enabled, Mastra logs this audit as a warning by default.
+
+For custom routes, prefer route-level `fga` metadata. This keeps authorization policy next to the route:
+
+```typescript
+import { createRoute } from '@mastra/server/server-adapter';
+
+export const getProjectRoute = createRoute({
+  method: 'GET',
+  path: '/projects/:projectId',
+  responseType: 'json',
+  requiresAuth: true,
+  fga: {
+    resourceType: 'project',
+    resourceIdParam: 'projectId',
+    permission: 'projects:read',
+  },
+  handler: async () => {
+    return { project: null };
+  },
+});
+```
+
+Use `resolveRouteFGA()` only when route metadata must be derived centrally from route, params, or request context. A route map scales better than string-prefix checks:
+
+```typescript
+import type { FGARouteConfig, FGARouteResolver } from '@mastra/core/auth/ee';
+
+const routeFGA = {
+  'GET /billing/:accountId': {
+    resourceType: 'account',
+    resourceIdParam: 'accountId',
+    permission: 'billing:read',
+  },
+} satisfies Record<string, FGARouteConfig>;
+
+const resolveRouteFGA: FGARouteResolver = ({ route }) => routeFGA[`${route.method} ${route.path}`];
+
+const fga = new MastraFGAWorkos({
+  /* ... */
+  resolveRouteFGA,
+});
+```
+
 ## Enforcement points
 
 When an FGA provider is configured, Mastra automatically checks authorization at these lifecycle points:
@@ -98,7 +166,7 @@ When an FGA provider is configured, Mastra automatically checks authorization at
 | Tool execution                         | `tools:execute`                                | `{ type: 'tool', id: toolName }`       |
 | Thread/memory access                   | `memory:read`, `memory:write`, `memory:delete` | `{ type: 'thread', id: threadId }`     |
 | MCP tool execution                     | `tools:execute`                                | `{ type: 'tool', id: toolName }`       |
-| HTTP routes (opt-in)                   | Configured per route                           | Configured per route                   |
+| HTTP resource routes                   | Configured per route                           | Configured per route                   |
 
 All checks are **no-ops when FGA is not configured**, maintaining backward compatibility.
 

package/.docs/models/index.md

@@ -1,6 +1,6 @@
 # Model Providers
 
-Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 3948 models from 115 providers through a single API.
+Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 3967 models from 118 providers through a single API.
 
 ## Features
 

package/.docs/models/providers/atomic-chat.md

@@ -0,0 +1,75 @@
+# ![Atomic Chat logo](https://models.dev/logos/atomic-chat.svg)Atomic Chat
+
+Access 5 Atomic Chat models through Mastra's model router. Authentication is handled automatically using the `ATOMIC_CHAT_API_KEY` environment variable.
+
+Learn more in the [Atomic Chat documentation](https://atomic.chat).
+
+```bash
+ATOMIC_CHAT_API_KEY=your-api-key
+```
+
+```typescript
+import { Agent } from "@mastra/core/agent";
+
+const agent = new Agent({
+  id: "my-agent",
+  name: "My Agent",
+  instructions: "You are a helpful assistant",
+  model: "atomic-chat/Meta-Llama-3_1-8B-Instruct-GGUF"
+});
+
+// Generate a response
+const response = await agent.generate("Hello!");
+
+// Stream a response
+const stream = await agent.stream("Tell me a story");
+for await (const chunk of stream) {
+  console.log(chunk);
+}
+```
+
+> **Info:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [Atomic Chat documentation](https://atomic.chat) for details.
+
+## Models
+
+| Model                                         | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
+| --------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
+| `atomic-chat/gemma-4-E4B-it-IQ4_XS`           | 33K     |       |           |       |       |       | —          | —           |
+| `atomic-chat/gemma-4-E4B-it-MLX-4bit`         | 33K     |       |           |       |       |       | —          | —           |
+| `atomic-chat/Meta-Llama-3_1-8B-Instruct-GGUF` | 131K    |       |           |       |       |       | —          | —           |
+| `atomic-chat/Qwen3_5-9B-MLX-4bit`             | 33K     |       |           |       |       |       | —          | —           |
+| `atomic-chat/Qwen3_5-9B-Q4_K_M`               | 33K     |       |           |       |       |       | —          | —           |
+
+## Advanced configuration
+
+### Custom headers
+
+```typescript
+const agent = new Agent({
+  id: "custom-agent",
+  name: "custom-agent",
+  model: {
+    url: "http://127.0.0.1:1337/v1",
+    id: "atomic-chat/Meta-Llama-3_1-8B-Instruct-GGUF",
+    apiKey: process.env.ATOMIC_CHAT_API_KEY,
+    headers: {
+      "X-Custom-Header": "value"
+    }
+  }
+});
+```
+
+### Dynamic model selection
+
+```typescript
+const agent = new Agent({
+  id: "dynamic-agent",
+  name: "Dynamic Agent",
+  model: ({ requestContext }) => {
+    const useAdvanced = requestContext.task === "complex";
+    return useAdvanced
+      ? "atomic-chat/gemma-4-E4B-it-MLX-4bit"
+      : "atomic-chat/Meta-Llama-3_1-8B-Instruct-GGUF";
+  }
+});
+```

package/.docs/models/providers/gmicloud.md

@@ -0,0 +1,78 @@
+# ![GMI Cloud logo](https://models.dev/logos/gmicloud.svg)GMI Cloud
+
+Access 8 GMI Cloud models through Mastra's model router. Authentication is handled automatically using the `GMICLOUD_API_KEY` environment variable.
+
+Learn more in the [GMI Cloud documentation](https://docs.gmicloud.ai).
+
+```bash
+GMICLOUD_API_KEY=your-api-key
+```
+
+```typescript
+import { Agent } from "@mastra/core/agent";
+
+const agent = new Agent({
+  id: "my-agent",
+  name: "My Agent",
+  instructions: "You are a helpful assistant",
+  model: "gmicloud/anthropic/claude-opus-4.6"
+});
+
+// Generate a response
+const response = await agent.generate("Hello!");
+
+// Stream a response
+const stream = await agent.stream("Tell me a story");
+for await (const chunk of stream) {
+  console.log(chunk);
+}
+```
+
+> **Info:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [GMI Cloud documentation](https://docs.gmicloud.ai) for details.
+
+## Models
+
+| Model                                    | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
+| ---------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
+| `gmicloud/anthropic/claude-opus-4.6`     | 410K    |       |           |       |       |       | $5         | $25         |
+| `gmicloud/anthropic/claude-opus-4.7`     | 410K    |       |           |       |       |       | $5         | $23         |
+| `gmicloud/anthropic/claude-sonnet-4.6`   | 410K    |       |           |       |       |       | $3         | $15         |
+| `gmicloud/deepseek-ai/DeepSeek-V4-Flash` | 1.0M    |       |           |       |       |       | $0.11      | $0.22       |
+| `gmicloud/deepseek-ai/DeepSeek-V4-Pro`   | 1.0M    |       |           |       |       |       | $1         | $3          |
+| `gmicloud/moonshotai/Kimi-K2.6`          | 66K     |       |           |       |       |       | $0.85      | $4          |
+| `gmicloud/zai-org/GLM-5-FP8`             | 203K    |       |           |       |       |       | $0.60      | $2          |
+| `gmicloud/zai-org/GLM-5.1-FP8`           | 203K    |       |           |       |       |       | $0.98      | $3          |
+
+## Advanced configuration
+
+### Custom headers
+
+```typescript
+const agent = new Agent({
+  id: "custom-agent",
+  name: "custom-agent",
+  model: {
+    url: "https://api.gmi-serving.com/v1",
+    id: "gmicloud/anthropic/claude-opus-4.6",
+    apiKey: process.env.GMICLOUD_API_KEY,
+    headers: {
+      "X-Custom-Header": "value"
+    }
+  }
+});
+```
+
+### Dynamic model selection
+
+```typescript
+const agent = new Agent({
+  id: "dynamic-agent",
+  name: "Dynamic Agent",
+  model: ({ requestContext }) => {
+    const useAdvanced = requestContext.task === "complex";
+    return useAdvanced
+      ? "gmicloud/zai-org/GLM-5.1-FP8"
+      : "gmicloud/anthropic/claude-opus-4.6";
+  }
+});
+```

package/.docs/models/providers/minimax-cn-coding-plan.md

@@ -1,8 +1,8 @@
-# ![MiniMax Coding Plan (minimaxi.com) logo](https://models.dev/logos/minimax-cn-coding-plan.svg)MiniMax Coding Plan (minimaxi.com)
+# ![MiniMax Token Plan (minimaxi.com) logo](https://models.dev/logos/minimax-cn-coding-plan.svg)MiniMax Token Plan (minimaxi.com)
 
-Access 6 MiniMax Coding Plan (minimaxi.com) models through Mastra's model router. Authentication is handled automatically using the `MINIMAX_API_KEY` environment variable.
+Access 6 MiniMax Token Plan (minimaxi.com) models through Mastra's model router. Authentication is handled automatically using the `MINIMAX_API_KEY` environment variable.
 
-Learn more in the [MiniMax Coding Plan (minimaxi.com) documentation](https://platform.minimaxi.com/docs/coding-plan/intro).
+Learn more in the [MiniMax Token Plan (minimaxi.com) documentation](https://platform.minimaxi.com/docs/token-plan/intro).
 
 ```bash
 MINIMAX_API_KEY=your-api-key
@@ -28,7 +28,7 @@ for await (const chunk of stream) {
 }
 ```
 
-> **Info:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [MiniMax Coding Plan (minimaxi.com) documentation](https://platform.minimaxi.com/docs/coding-plan/intro) for details.
+> **Info:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [MiniMax Token Plan (minimaxi.com) documentation](https://platform.minimaxi.com/docs/token-plan/intro) for details.
 
 ## Models
 

package/.docs/models/providers/minimax-coding-plan.md

@@ -1,8 +1,8 @@
-# ![MiniMax Coding Plan (minimax.io) logo](https://models.dev/logos/minimax-coding-plan.svg)MiniMax Coding Plan (minimax.io)
+# ![MiniMax Token Plan (minimax.io) logo](https://models.dev/logos/minimax-coding-plan.svg)MiniMax Token Plan (minimax.io)
 
-Access 6 MiniMax Coding Plan (minimax.io) models through Mastra's model router. Authentication is handled automatically using the `MINIMAX_API_KEY` environment variable.
+Access 6 MiniMax Token Plan (minimax.io) models through Mastra's model router. Authentication is handled automatically using the `MINIMAX_API_KEY` environment variable.
 
-Learn more in the [MiniMax Coding Plan (minimax.io) documentation](https://platform.minimax.io/docs/coding-plan/intro).
+Learn more in the [MiniMax Token Plan (minimax.io) documentation](https://platform.minimax.io/docs/token-plan/intro).
 
 ```bash
 MINIMAX_API_KEY=your-api-key
@@ -28,7 +28,7 @@ for await (const chunk of stream) {
 }
 ```
 
-> **Info:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [MiniMax Coding Plan (minimax.io) documentation](https://platform.minimax.io/docs/coding-plan/intro) for details.
+> **Info:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [MiniMax Token Plan (minimax.io) documentation](https://platform.minimax.io/docs/token-plan/intro) for details.
 
 ## Models
 

package/.docs/models/providers/opencode.md

@@ -1,6 +1,6 @@
 # ![OpenCode Zen logo](https://models.dev/logos/opencode.svg)OpenCode Zen
 
-Access 39 OpenCode Zen models through Mastra's model router. Authentication is handled automatically using the `OPENCODE_API_KEY` environment variable.
+Access 40 OpenCode Zen models through Mastra's model router. Authentication is handled automatically using the `OPENCODE_API_KEY` environment variable.
 
 Learn more in the [OpenCode Zen documentation](https://opencode.ai/docs/zen).
 
@@ -73,6 +73,7 @@ for await (const chunk of stream) {
 | `opencode/nemotron-3-super-free`  | 205K    |       |           |       |       |       | —          | —           |
 | `opencode/qwen3.5-plus`           | 262K    |       |           |       |       |       | $0.20      | $1          |
 | `opencode/qwen3.6-plus`           | 262K    |       |           |       |       |       | $0.50      | $3          |
+| `opencode/qwen3.6-plus-free`      | 262K    |       |           |       |       |       | —          | —           |
 
 ## Advanced configuration
 
@@ -102,7 +103,7 @@ const agent = new Agent({
   model: ({ requestContext }) => {
     const useAdvanced = requestContext.task === "complex";
     return useAdvanced
-      ? "opencode/qwen3.6-plus"
+      ? "opencode/qwen3.6-plus-free"
       : "opencode/big-pickle";
   }
 });

package/.docs/models/providers/umans-ai-coding-plan.md

@@ -0,0 +1,75 @@
+# ![Umans AI Coding Plan logo](https://models.dev/logos/umans-ai-coding-plan.svg)Umans AI Coding Plan
+
+Access 5 Umans AI Coding Plan models through Mastra's model router. Authentication is handled automatically using the `UMANS_AI_CODING_PLAN_API_KEY` environment variable.
+
+Learn more in the [Umans AI Coding Plan documentation](https://app.umans.ai/offers/code/docs).
+
+```bash
+UMANS_AI_CODING_PLAN_API_KEY=your-api-key
+```
+
+```typescript
+import { Agent } from "@mastra/core/agent";
+
+const agent = new Agent({
+  id: "my-agent",
+  name: "My Agent",
+  instructions: "You are a helpful assistant",
+  model: "umans-ai-coding-plan/umans-coder"
+});
+
+// Generate a response
+const response = await agent.generate("Hello!");
+
+// Stream a response
+const stream = await agent.stream("Tell me a story");
+for await (const chunk of stream) {
+  console.log(chunk);
+}
+```
+
+> **Info:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [Umans AI Coding Plan documentation](https://app.umans.ai/offers/code/docs) for details.
+
+## Models
+
+| Model                                        | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
+| -------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
+| `umans-ai-coding-plan/umans-coder`           | 262K    |       |           |       |       |       | —          | —           |
+| `umans-ai-coding-plan/umans-flash`           | 262K    |       |           |       |       |       | —          | —           |
+| `umans-ai-coding-plan/umans-glm-5.1`         | 205K    |       |           |       |       |       | —          | —           |
+| `umans-ai-coding-plan/umans-kimi-k2.6`       | 262K    |       |           |       |       |       | —          | —           |
+| `umans-ai-coding-plan/umans-qwen3.6-35b-a3b` | 262K    |       |           |       |       |       | —          | —           |
+
+## Advanced configuration
+
+### Custom headers
+
+```typescript
+const agent = new Agent({
+  id: "custom-agent",
+  name: "custom-agent",
+  model: {
+    url: "https://api.code.umans.ai/v1",
+    id: "umans-ai-coding-plan/umans-coder",
+    apiKey: process.env.UMANS_AI_CODING_PLAN_API_KEY,
+    headers: {
+      "X-Custom-Header": "value"
+    }
+  }
+});
+```
+
+### Dynamic model selection
+
+```typescript
+const agent = new Agent({
+  id: "dynamic-agent",
+  name: "Dynamic Agent",
+  model: ({ requestContext }) => {
+    const useAdvanced = requestContext.task === "complex";
+    return useAdvanced
+      ? "umans-ai-coding-plan/umans-qwen3.6-35b-a3b"
+      : "umans-ai-coding-plan/umans-coder";
+  }
+});
+```

package/.docs/models/providers/xpersona.md

@@ -34,7 +34,7 @@ for await (const chunk of stream) {
 
 | Model                             | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
 | --------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
-| `xpersona/xpersona-frieren-coder` | 128K    |       |           |       |       |       | $2         | $6          |
+| `xpersona/xpersona-frieren-coder` | 400K    |       |           |       |       |       | $2         | $6          |
 
 ## Advanced configuration
 

package/.docs/models/providers.md

@@ -17,6 +17,7 @@ Direct access to individual AI model providers. Each provider offers unique mode
 - [Alibaba Coding Plan](https://mastra.ai/models/providers/alibaba-coding-plan)
 - [Alibaba Coding Plan (China)](https://mastra.ai/models/providers/alibaba-coding-plan-cn)
 - [Ambient](https://mastra.ai/models/providers/ambient)
+- [Atomic Chat](https://mastra.ai/models/providers/atomic-chat)
 - [Auriko](https://mastra.ai/models/providers/auriko)
 - [Bailing](https://mastra.ai/models/providers/bailing)
 - [Baseten](https://mastra.ai/models/providers/baseten)
@@ -40,6 +41,7 @@ Direct access to individual AI model providers. Each provider offers unique mode
 - [Friendli](https://mastra.ai/models/providers/friendli)
 - [FrogBot](https://mastra.ai/models/providers/frogbot)
 - [GitHub Models](https://mastra.ai/models/providers/github-models)
+- [GMI Cloud](https://mastra.ai/models/providers/gmicloud)
 - [Helicone](https://mastra.ai/models/providers/helicone)
 - [HPC-AI](https://mastra.ai/models/providers/hpc-ai)
 - [Hugging Face](https://mastra.ai/models/providers/huggingface)
@@ -58,8 +60,8 @@ Direct access to individual AI model providers. Each provider offers unique mode
 - [Meganova](https://mastra.ai/models/providers/meganova)
 - [MiniMax (minimax.io)](https://mastra.ai/models/providers/minimax)
 - [MiniMax (minimaxi.com)](https://mastra.ai/models/providers/minimax-cn)
-- [MiniMax Coding Plan (minimax.io)](https://mastra.ai/models/providers/minimax-coding-plan)
-- [MiniMax Coding Plan (minimaxi.com)](https://mastra.ai/models/providers/minimax-cn-coding-plan)
+- [MiniMax Token Plan (minimax.io)](https://mastra.ai/models/providers/minimax-coding-plan)
+- [MiniMax Token Plan (minimaxi.com)](https://mastra.ai/models/providers/minimax-cn-coding-plan)
 - [Mixlayer](https://mastra.ai/models/providers/mixlayer)
 - [Moark](https://mastra.ai/models/providers/moark)
 - [ModelScope](https://mastra.ai/models/providers/modelscope)
@@ -97,6 +99,7 @@ Direct access to individual AI model providers. Each provider offers unique mode
 - [Tencent TokenHub](https://mastra.ai/models/providers/tencent-tokenhub)
 - [The Grid AI](https://mastra.ai/models/providers/the-grid-ai)
 - [Together AI](https://mastra.ai/models/providers/togetherai)
+- [Umans AI Coding Plan](https://mastra.ai/models/providers/umans-ai-coding-plan)
 - [Upstage](https://mastra.ai/models/providers/upstage)
 - [Vivgrid](https://mastra.ai/models/providers/vivgrid)
 - [Vultr](https://mastra.ai/models/providers/vultr)

package/CHANGELOG.md

@@ -1,5 +1,19 @@
 # @mastra/mcp-docs-server
 
+## 1.1.38-alpha.2
+
+### Patch Changes
+
+- Updated dependencies [[`bad08e9`](https://github.com/mastra-ai/mastra/commit/bad08e99c5291884c3ac76743c78c74f53a302c2)]:
+  - @mastra/core@1.35.0-alpha.1
+
+## 1.1.38-alpha.0
+
+### Patch Changes
+
+- Updated dependencies [[`b661349`](https://github.com/mastra-ai/mastra/commit/b661349281514691db78941a9044e6e4f1cde7a7)]:
+  - @mastra/core@1.34.1-alpha.0
+
 ## 1.1.37
 
 ### Patch Changes

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mastra/mcp-docs-server",
-  "version": "1.1.37",
+  "version": "1.1.38-alpha.3",
   "description": "MCP server for accessing Mastra.ai documentation, changelogs, and news.",
   "type": "module",
   "main": "dist/index.js",
@@ -29,8 +29,8 @@
     "jsdom": "^26.1.0",
     "local-pkg": "^1.1.2",
     "zod": "^4.3.6",
-    "@mastra/mcp": "^1.7.0",
-    "@mastra/core": "1.34.0"
+    "@mastra/core": "1.35.0-alpha.1",
+    "@mastra/mcp": "^1.7.0"
   },
   "devDependencies": {
     "@hono/node-server": "^1.19.11",
@@ -48,7 +48,7 @@
     "vitest": "4.1.5",
     "@internal/lint": "0.0.95",
     "@internal/types-builder": "0.0.70",
-    "@mastra/core": "1.34.0"
+    "@mastra/core": "1.35.0-alpha.1"
   },
   "homepage": "https://mastra.ai",
   "repository": {