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

Q: How do I connect Cohere (Embed & Rerank) to my Mastra AI workflows?

Install @mastra/mcp and instantiate a new MCPClient with your Vinkius server URL. Call mcpClient.listTools() and spread them directly into your Mastra agent's tool array.

Q: Does Cohere (Embed & Rerank) support human-in-the-loop steps in Mastra AI?

It does. You can configure Mastra's requireToolApproval flag on sensitive tools like chatcompletion or classifytexts, allowing operators to review the agent's actions before they execute.

Q: How do I know which Cohere models are available in my workflow?

You can call listmodels directly from your workflow to query the active API capabilities. This lets your agents adapt to new model versions without requiring manual code updates.

Build complex, self-healing semantic search workflows in Mastra AI using Cohere's production-grade embeddings and reranking.

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 Mastra AI

Create your Vinkius account to connect Cohere (Embed & Rerank) to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resilient search pipelines with Mastra AI and MCP

Mastra AI excels at handling complex workflows where things can go wrong. By connecting this MCP Server, you can build a workflow that runs `embed_texts` and automatically falls back to a different model or triggers an alert if the primary API call fails. Your agent can use `rerank_documents` to filter search results, passing only high-confidence matches to the next step. If no documents pass your relevance threshold, Mastra's routing logic can branch to run a broader search.

Automated content classification and routing

Turn incoming unstructured text into organized data pipelines. Use `classify_texts` within a Mastra workflow to automatically categorize user feedback, support issues, or emails as they arrive. Once the server categorizes the text, Mastra's engine routes the output to the correct handler. If the classification confidence is low, you can trigger a human-in-the-loop approval step before executing the next action.

Context-aware conversational loops

Keep your agent's memory sharp and relevant. By calling `tokenize_text` inside your agent loop, you can measure the exact size of your conversation logs before submitting them. If the token count is too high, use `chat_completion` to summarize past turns or compress the history. This keeps your workflows running efficiently without hitting API context limits.

Setup guide

Set up Cohere (Embed & Rerank) MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. 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's tools object. All Cohere (Embed & Rerank) tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "cohere-embed-rerank-mcp-client",
  servers: {
    "cohere-embed-rerank-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Cohere (Embed & Rerank) Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Cohere (Embed & Rerank) tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Cohere (Embed & Rerank) transactions"
);
console.log(result.text);

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 Mastra AI

Install `@mastra/mcp` and instantiate a new `MCPClient` with your Vinkius server URL. Call `mcpClient.listTools()` and spread them directly into your Mastra agent's tool array.

Yes, Mastra's workflow engine has built-in exponential backoff. If you hit a rate limit while running heavy batch jobs with `embed_texts`, the framework automatically retries the call until it succeeds.

It does. You can configure Mastra's `requireToolApproval` flag on sensitive tools like `chat_completion` or `classify_texts`, allowing operators to review the agent's actions before they execute.

You can call `list_models` directly from your workflow to query the active API capabilities. This lets your agents adapt to new model versions without requiring manual code updates.

All text strings, document arrays, and vector shapes are processed in an isolated, ephemeral sandbox. Vinkius handles the MCP authorization securely and destroys the processing environment as soon as the execution completes.

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