How to Use the Cognita (RAG Framework) MCP in Vercel AI SDK

Q: How do I handle streaming responses from Cognita (RAG Framework) using Vercel AI SDK?

You pass the ragquery tool from the MCP Server directly into the tools parameter of streamText. This lets your Vercel AI SDK frontend render the generated RAG answers token-by-token as Cognita processes the transformation vectors.

Q: Can I ingest new documents into Cognita (RAG Framework) directly from a Vercel AI SDK chat interface?

Yes, you use the ingestdata tool within your Vercel AI SDK tool-calling block to send raw payloads to Cognita. The server provisions the highly-available JSON payload and returns the new resource directory structure to your UI.

Q: How does the Vercel AI SDK handle Cognita (RAG Framework) collection routing?

Your code calls listcollections to find bounded routing spaces within the Cognita limit. This allows your Vercel AI SDK application to dynamically direct user queries to the correct vector index based on their current chat session context.

Q: How do I close the MCP connection in Vercel serverless functions?

Always call mcpClient.close() once your Vercel AI SDK text generation finishes. This prevents lingering HTTP or SSE connections from exhausting your serverless execution limits.

Q: Is my vector chunk data safe when querying Cognita with this MCP setup?

All vector chunks and trace logs processed by searchchunks run inside a zero-trust V8 Isolate sandbox on Vinkius. Your raw JSON payloads never touch persistent external storage during the ingestion phase.

Stream Cognita (RAG Framework) vector searches and Q&A directly into your Vercel AI SDK frontend in real-time.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cognita (RAG Framework) MCP to Vercel AI SDK

Create your Vinkius account to connect Cognita (RAG Framework) to Vercel AI SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Cognita (RAG Framework) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Cognita queries live in Vercel AI SDK

The `rag_query` tool connects your React or Next.js frontend directly to Cognita's rented Transformation vectors via the Vercel AI SDK. Instead of staring at a blank loading screen, your users watch the RAG synthesis unfold word-by-word as the MCP Server streams the response. It's a night-and-day difference for user experience. You feed the tool output directly into `streamText` to render live answers. By combining `get_collection` with Vercel's edge-compatible runtime, you pull explicit Cloud logging traces into the UI without adding latency.

Real-time data ingestion through Vercel AI SDK

The `ingest_data` tool lets your Vercel AI SDK application provision highly-available JSON payloads and generate new resource directories on the fly. Your users can drop raw text or documents directly into their chat window, and your app instantly ingests them into active Cognita buckets. You don't want users waiting on a spinner while things update. To keep the UI responsive, use `list_data_sources` to extract structural properties of these active buckets and update the user's sidebar.

Inspect RAG collections in edge functions

The `list_collections` tool identifies bounded routing spaces inside your Headless Cognita RAG limits directly from a Vercel AI SDK edge route. This avoids cold starts and keeps your routing logic fast when mapping queries to specific vector spaces using this MCP Server. Pair this with `search_chunks` to pull structured rules and active presets into your edge runtime. Your application can immediately display which chunking rules are active before the user even submits their search query.

Setup guide

Set up Cognita (RAG Framework) MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Cognita (RAG Framework) tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Cognita (RAG Framework) transactions",
});

console.log(text);
await mcpClient.close();

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Cognita. 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.

Connect Cognita (RAG Framework) now

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 Cognita (RAG Framework) MCP in Vercel AI SDK

You pass the `rag_query` tool from the MCP Server directly into the `tools` parameter of `streamText`. This lets your Vercel AI SDK frontend render the generated RAG answers token-by-token as Cognita processes the transformation vectors.

Yes, you use the `ingest_data` tool within your Vercel AI SDK tool-calling block to send raw payloads to Cognita. The server provisions the highly-available JSON payload and returns the new resource directory structure to your UI.

Your code calls `list_collections` to find bounded routing spaces within the Cognita limit. This allows your Vercel AI SDK application to dynamically direct user queries to the correct vector index based on their current chat session context.

Always call `mcpClient.close()` once your Vercel AI SDK text generation finishes. This prevents lingering HTTP or SSE connections from exhausting your serverless execution limits.

All vector chunks and trace logs processed by `search_chunks` run inside a zero-trust V8 Isolate sandbox on Vinkius. Your raw JSON payloads never touch persistent external storage during the ingestion phase.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript