How to Use the Cohere MCP in Mastra AI

Q: Can Mastra AI workflows use Cohere embeddings for RAG?

Yes, you can use the embed tool inside a workflow step to vectorize incoming text. The resulting vectors can then be queried against your vector database.

Q: Can I require human approval before running a Cohere tool?

Yes, you can set requireToolApproval on tools like chat or rerank in Mastra AI. This holds the workflow until an operator reviews the proposed action.

Build resilient, self-healing Mastra AI workflows powered by Cohere's advanced reranking and chat models.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cohere MCP to Mastra AI

Create your Vinkius account to connect Cohere 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 with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Route Mastra AI tasks using Cohere embeddings

The Cohere `embed` tool generates high-dimensional vectors from incoming customer tickets to determine their intent. Workflows built in Mastra use these Cohere vectors to branch your execution path, sending technical issues to engineers and billing questions to accounting. Because this Cohere MCP Server integrates directly with Mastra's workflow engine, you can build conditional branches based on semantic similarity. Your Mastra AI agents make decisions based on Cohere's vector space rather than fragile keyword matching.

Rerank workflow context on the fly

The Cohere `rerank` tool acts as a gatekeeper in your Mastra AI retrieval pipelines, sorting through hundreds of raw database documents to find the top three matches. This ensures your Mastra agents only read the most relevant data, reducing Cohere token overhead and hallucinations. That's how you keep your Mastra agent context windows clean and your Cohere API bills predictable. You can configure this Cohere reranking step as a Mastra workflow node that automatically triggers before the main generation step.

Dynamic model selection for Mastra AI agents

The Cohere `list_models` tool queries available endpoints so your Mastra workflow can switch models dynamically if one experiences high latency. If Command-R-Plus is sluggish, your Mastra AI agent can fall back to a lighter Cohere model automatically. This programmatic flexibility keeps your Mastra production pipelines running without manual intervention. You write the fallback logic once, and the Mastra framework handles the rest using current Cohere model metadata accessed via MCP.

Setup guide

Set up Cohere 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 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-mcp-client",
  servers: {
    "cohere-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent Cohere 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 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 MCP in Mastra AI

Initialize the MCP client in your Mastra setup and spread the returned tools into your agent's configuration. This immediately grants the agent access to the `chat` and `rerank` functions.

Yes, you can use the `embed` tool inside a workflow step to vectorize incoming text. The resulting vectors can then be queried against your vector database.

Mastra's built-in workflow engine handles rate limits automatically using exponential backoff. If the `chat` tool returns a rate limit error, the workflow pauses and retries without dropping the execution state.

Yes, you can set `requireToolApproval` on tools like `chat` or `rerank` in Mastra AI. This holds the workflow until an operator reviews the proposed action.

All text strings, query vectors, and document arrays are processed in memory within an ephemeral V8 sandbox hosting the MCP Server. We enforce zero-trust network policies, meaning your data is never written to disk or used for training.

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