How to Use the ThinkStack MCP in Mastra AI
Show your users the AI working live with Mastra AI.
Works with every AI agent you already use
…and any MCP-compatible client
Connect ThinkStack MCP to Mastra AI
Create your Vinkius account to connect ThinkStack to Mastra AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.
Key Capabilities
Stream Real-Time Queries
You can send a query using `send_query` and stream the results directly into the UI. This means your user sees the data appearing immediately, not after some loading spinner kicks in. This is critical for building frontends where live feedback matters. The agent uses the result to populate components as it gets them, making the entire interaction feel snappy.
Manage Knowledge Sources
`add_source` lets you feed the system new content that the AI needs for context. You can also list what's available with `list_sources`, so you know exactly which documents are powering the responses. If you need to pull data or remove old material, use `delete_source`. It keeps your knowledge base clean and relevant for the user-facing product.
Track Conversation Context
When a conversation gets complicated, you need history. The tool `get_conversation` pulls all past turns so the agent remembers what was said earlier. You can also list all threads using `list_conversations`, keeping your product's state visible. This context is key when building complex user flows in Next.js or Svelte; it prevents the AI from giving irrelevant answers.
Set up ThinkStack MCP in Mastra AI
Prerequisites
- Node.js 18+ and a TypeScript project
-
@mastra/mcp+@mastra/corepackages - Active Vinkius subscription with a valid endpoint token
- 1
Install dependencies
Run
npm install @mastra/mcp @mastra/coreplus your preferred model provider (e.g.@ai-sdk/openai). - 2
Configure the MCPClient
Create an
MCPClientwith your Vinkius endpoint as aURLobject. Replace[YOUR_TOKEN_HERE]with your token from cloud.vinkius.com. - 3
Discover and inject tools
Call
mcpClient.listTools()and spread the result into your agent'stoolsobject. All ThinkStack tools become native Mastra tools. - 4
Run with any model
Swap
openai("gpt-4o")for any AI SDK-compatible provider. Callagent.generate()and the agent routes tool calls through MCP automatically.
import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";
const mcpClient = new MCPClient({
id: "thinkstack-mcp-client",
servers: {
"thinkstack-mcp": {
url: new URL(
"https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
),
},
},
});
const agent = new Agent({
name: "ThinkStack Agent",
model: openai("gpt-4o"),
instructions: "You have access to ThinkStack tools.",
tools: {
...(await mcpClient.listTools()),
},
});
const result = await agent.generate(
"List recent ThinkStack transactions"
);
console.log(result.text); Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by ThinkStack. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
Why Choose Vinkius
Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.
Real-time monitoring
Live
visibility into every interaction
Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.
Built-in savings
60%
lower AI costs
Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.
Single dashboard
One
place for every integration
Every tool your AI connects to, managed from a single screen. One account, complete control.
Common questions about ThinkStack MCP in Mastra AI
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
Start using the ThinkStack MCP today
We host it, we monitor it, we maintain it. You just paste one token.