@mastra/mcp-docs-server 0.13.28 → 0.13.29-alpha.1

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mastra/mcp-docs-server",
-  "version": "0.13.28",
+  "version": "0.13.29-alpha.1",
   "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.1",
     "@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.1"
   },
   "homepage": "https://mastra.ai",
   "repository": {

package/.docs/raw/agents/dynamic-agents.mdx

@@ -1,121 +0,0 @@
----
-title: "Dynamic Agents"
-description: Dynamically configure your agent's instruction, model, tools, and memory using runtime context.
----
-
-# Dynamic Agents
-
-Dynamic agents use [runtime context](./runtime-context), like user IDs and other important parameters, to adjust their settings in real-time.
-
-This means they can change the model they use, update their instructions, select different tools, and configure memory as needed.
-
-By using this context, agents can better respond to each user's needs. They can also call any API to gather more information, which helps improve what the agents can do.
-
-### Example Configuration
-
-Here's an example of a dynamic support agent that adjusts its behavior based on the user's subscription tier and language preferences:
-
-```typescript
-const supportAgent = new Agent({
-  name: "Dynamic Support Agent",
-
-  instructions: async ({ runtimeContext }) => {
-    const userTier = runtimeContext.get("user-tier");
-    const language = runtimeContext.get("language");
-
-    // Can return a string
-    return `You are a customer support agent for our SaaS platform.
-    The current user is on the ${userTier} tier and prefers ${language} language.
-
-    For ${userTier} tier users:
-    ${userTier === "free" ? "- Provide basic support and documentation links" : ""}
-    ${userTier === "pro" ? "- Offer detailed technical support and best practices" : ""}
-    ${userTier === "enterprise" ? "- Provide priority support with custom solutions" : ""}
-
-    Always respond in ${language} language.`;
-    
-    // Alternative: Return a system message object with provider options
-    // return {
-    //   role: "system",
-    //   content: `You are a customer support agent for ${userTier} tier...`,
-    //   providerOptions: {
-    //     openai: { 
-    //       reasoning_effort: userTier === "enterprise" ? "high" : "medium"
-    //     }
-    //   }
-    // };
-    
-    // Alternative: Return an array of system messages for modular instructions
-    // return [
-    //   { role: "system", content: "You are a customer support agent." },
-    //   { role: "system", content: `User is on ${userTier} tier.` },
-    //   { role: "system", content: `Respond in ${language} language.` }
-    // ];
-  },
-
-  model: ({ runtimeContext }) => {
-    const userTier = runtimeContext.get("user-tier");
-    return userTier === "enterprise"
-      ? openai("gpt-4")
-      : openai("gpt-3.5-turbo");
-  },
-
-  tools: ({ runtimeContext }) => {
-    const userTier = runtimeContext.get("user-tier");
-    const baseTools = [knowledgeBase, ticketSystem];
-
-    if (userTier === "pro" || userTier === "enterprise") {
-      baseTools.push(advancedAnalytics);
-    }
-
-    if (userTier === "enterprise") {
-      baseTools.push(customIntegration);
-    }
-
-    return baseTools;
-  },
-
-  memory: ({ runtimeContext }) => {
-    const userTier = runtimeContext.get("user-tier");
-
-    if (userTier === "enterprise") {
-      return new Memory({
-        storage: new LibSQLStore({ url: "file:enterprise.db" }),
-        options: {
-          semanticRecall: { topK: 15, messageRange: 8 },
-          workingMemory: { enabled: true },
-        },
-      });
-    } else if (userTier === "pro") {
-      return new Memory({
-        storage: new LibSQLStore({ url: "file:pro.db" }),
-        options: {
-          semanticRecall: { topK: 8, messageRange: 4 },
-          workingMemory: { enabled: true },
-        },
-      });
-    }
-
-    // Basic memory for free tier
-    return new Memory({
-      storage: new LibSQLStore({ url: "file:free.db" }),
-      options: {
-        semanticRecall: { topK: 3, messageRange: 2 },
-        workingMemory: { enabled: false },
-      },
-    });
-  },
-});
-```
-
-In this example, the agent:
-
-- Adjusts its instructions based on the user's subscription tier (free, pro, or enterprise)
-- Uses a more powerful model (GPT-4) for enterprise users
-- Provides different sets of tools based on the user's tier
-- Configures memory with different capabilities based on the user's tier
-- Responds in the user's preferred language
-
-This demonstrates how a single agent can handle different types of users and scenarios by leveraging runtime context, making it more flexible and maintainable than creating separate agents for each use case.
-
-For a complete implementation example including API routes, middleware setup, and runtime context handling, see our [Dynamic Agents Example](/examples/agents/dynamic-agents).