How to Use the Cohere (Embed & Rerank) MCP in Vercel AI SDK

Q: How do I set up the Cohere (Embed & Rerank) MCP Server with Vercel AI SDK?

Install @ai-sdk/mcp and ai. Create an MCP client pointing to your Vinkius endpoint URL, pull the tools via mcpClient.tools(), and pass them straight into streamText. Don't forget to call mcpClient.close() once your edge function finishes.

Q: Does the Cohere (Embed & Rerank) integration support model selection in Vercel AI SDK?

It does. You can run listmodels to check which Cohere embedding and reranking models are currently available on your endpoint. This lets your application dynamically swap models based on the task size or language.

Run Cohere embeddings and reranking directly in your Vercel AI SDK apps to stream semantic search results live to your users.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cohere (Embed & Rerank) MCP to Vercel AI SDK

Create your Vinkius account to connect Cohere (Embed & Rerank) 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 Cohere (Embed & Rerank) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Cohere search results in Vercel AI SDK

Stop making users stare at loading spinners while your app fetches search results. This MCP Server lets your application call `rerank_documents` and stream the sorted, highly relevant chunks straight to your React or Next.js frontend as they resolve. By hooking this into your stream, your agent uses `embed_texts` to turn user queries into vectors, matches them, and feeds the top results to the UI. Your users get answers instantly instead of waiting for a slow backend database roundtrip to finish.

Structured text classification at the Edge

Running classification on Edge Functions requires lightweight, fast tools. By calling `classify_texts` through this integration, your Vercel AI SDK application can tag incoming user text, analyze sentiment, or route support tickets without heavy cold starts. Because the Vinkius platform runs these MCP connections in isolated V8 sandboxes, your edge middleware stays fast and secure. You get clean, categorized strings back instantly to update your UI state on the fly.

Dynamic token budgeting for streaming chats

When streaming long conversational responses, you need to manage your context window strictly. Use `tokenize_text` to check exactly how many tokens your prompt is eating up before you hit the API. Combine this with `chat_completion` to run quick, formatted text transformations. Your agent keeps its memory clean and your API bills predictable by pruning context in real-time.

Setup guide

Set up Cohere (Embed & Rerank) 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 Cohere (Embed & Rerank) 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 Cohere (Embed & Rerank) 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 Cohere. 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 Cohere (Embed & Rerank) 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 Cohere (Embed & Rerank) MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and `ai`. Create an MCP client pointing to your Vinkius endpoint URL, pull the tools via `mcpClient.tools()`, and pass them straight into `streamText`. Don't forget to call `mcpClient.close()` once your edge function finishes.

Yes, the entire setup is compatible with edge runtimes. Since Vinkius hosts the MCP Server on a zero-trust V8 sandbox, your edge functions don't need to manage heavy dependencies or long-lived connections.

It does. You can run `list_models` to check which Cohere embedding and reranking models are currently available on your endpoint. This lets your application dynamically swap models based on the task size or language.

Basic vector matching finds similar words, but reranking evaluates the actual meaning of the text chunks against the query. Running Cohere's reranker on your initial search results ensures your agent gets the absolute best context for its answers.

Your raw text, document chunks, and embeddings are processed inside transient, ephemeral V8 sandboxes. Vinkius never retains or logs the body of your strings, ensuring your search queries and database documents remain completely private.

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