Skip to main content
The Mastra adapter allows you to use AgentMark prompts with Mastra’s agentic workflow framework.

​
Installation

npm install @agentmark-ai/mastra-v0-adapter @mastra/core

​
Setup

Create your AgentMark client with a MastraModelRegistry. Use .registerModels() to map model names to Mastra model instances:
agentmark.client.ts
import { createAgentMarkClient, MastraModelRegistry } from "@agentmark-ai/mastra-v0-adapter";

const modelRegistry = new MastraModelRegistry()
  .registerModels(["claude-3-5-sonnet-20241022"], (name) => ({
    provider: "ANTHROPIC",
    name,
    apiKey: process.env.ANTHROPIC_API_KEY!,
  }))
  .registerModels(["gpt-4o"], (name) => ({
    provider: "OPENAI",
    name,
    apiKey: process.env.OPENAI_API_KEY!,
  }));

export const client = createAgentMarkClient({
  loader: fileLoader,
  modelRegistry,
});

​
Running Prompts

AgentMark prompts return Mastra agents via formatAgent(), which you can then use with formatMessages(): 
import { client } from "./agentmark.client";

const prompt = await client.loadTextPrompt("greeting.prompt.mdx");
const agent = await prompt.formatAgent({
  props: { name: "Alice" },
});

const [messages, options] = agent.formatMessages();
const result = await agent.generate(messages, options);

console.log(result.text);

​
Object Generation

For structured output, use object prompts: 
import { client } from "./agentmark.client";
import { z } from "zod";

const prompt = await client.loadObjectPrompt("extract.prompt.mdx", {
  schema: z.object({
    sentiment: z.enum(["positive", "negative", "neutral"]),
    confidence: z.number(),
  }),
});

const agent = await prompt.formatAgent({
  props: { text: "This product is amazing!" },
});

const [messages, options] = agent.formatMessages();
const result = await agent.generate(messages, options);

console.log(result.object);
// { sentiment: 'positive', confidence: 0.95 }

​
Streaming

Stream responses using agent.stream(): 
const prompt = await client.loadTextPrompt("story.prompt.mdx");
const agent = await prompt.formatAgent({
  props: { topic: "space exploration" },
});

const [messages, options] = agent.formatMessages();
const stream = await agent.stream(messages, options);

for await (const chunk of stream) {
  process.stdout.write(chunk);
}

​
Tools

Configure tools in your client:
agentmark.client.ts
import { createAgentMarkClient, MastraModelRegistry } from "@agentmark-ai/mastra-v0-adapter";
import { createTool } from "@mastra/core/tools";
import { z } from "zod";

const weatherTool = createTool({
  id: "weather",
  description: "Get current weather for a location",
  inputSchema: z.object({
    location: z.string(),
  }),
  execute: async ({ context }) => {
    const { location } = context;
    return `The weather in ${location} is sunny and 72°F`;
  },
});

export const client = createAgentMarkClient({
  loader: fileLoader,
  modelRegistry,
  tools: {
    weather: weatherTool,
  },
});
Then reference tools in your prompts:
weather.prompt.mdx
---
name: weather
text_config:
  model_name: claude-3-5-sonnet-20241022
  tools:
    - weather
---

<System>You are a helpful weather assistant.</System>
<User>What's the weather in {props.location}?</User>

​
MCP Servers

Configure MCP servers for extended capabilities:
agentmark.client.ts
import { createAgentMarkClient, MastraModelRegistry } from "@agentmark-ai/mastra-v0-adapter";

export const client = createAgentMarkClient({
  loader: fileLoader,
  modelRegistry,
  mcpServers: {
    filesystem: {
      command: "npx",
      args: ["-y", "@modelcontextprotocol/server-filesystem", "/path/to/files"],
    },
  },
});

​
Limitations

​
Next Steps

Prompts

Learn about prompt syntax

Testing

Test your prompts with datasets

Observability

Monitor your agents in production

Other Integrations

Explore other AI frameworks

​
Have Questions?

We’re here to help! Choose the best way to reach us: