How do I get a Cohere API Key?

Log in to the [**Cohere Dashboard**](https://dashboard.cohere.com/api-keys), go to **API Keys** and click **Create API Key**. Copy the key immediately — it starts with a random string and won't be shown again. Free tier includes trial access with rate limits.

What models are available?

Use the `list_models` tool to see all available Cohere models. Key models include command-r-plus (most capable, 128K context), command-r (efficient, 128K context), command-r7b (lightweight, 128K context), embed-v4 (embeddings) and rerank-v3.5 (reranking).

Can I send multi-turn conversations?

Yes! Pass a messages array with alternating 'user', 'assistant' and 'system' roles. Each message has a 'role' and 'content' field. Command models support function calling and will return tool_calls when appropriate.

What is reranking and when should I use it?

Reranking reorders a set of documents by their relevance to a query. Use it after an initial search to improve result quality. The rerank tool takes a query, list of documents and returns them ranked by relevance score. Cohere's rerank models are industry-leading for search applications.

Cohere MCP Server for Mastra AI 6 tools — connect in under 2 minutes

Name: Cohere
Availability: InStock
Author: Vinkius

docs.mastra.ai/docs/agents/mcp-tools

Built by Vinkius GDPR 6 Tools SDK

Mastra AI is a TypeScript-native agent framework built for modern web stacks. Connect Cohere through the Vinkius and Mastra agents discover all tools automatically — type-safe, streaming-ready, and deployable anywhere Node.js runs.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

typescript

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

async function main() {
  // Your Vinkius token — get it at cloud.vinkius.com
  const mcpClient = await createMCPClient({
    servers: {
      "cohere": {
        url: "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
      },
    },
  });

  const tools = await mcpClient.getTools();
  const agent = new Agent({
    name: "Cohere Agent",
    instructions:
      "You help users interact with Cohere " +
      "using 6 tools.",
    model: openai("gpt-4o"),
    tools,
  });

  const result = await agent.generate(
    "What can I do with Cohere?"
  );
  console.log(result.text);
}

main();

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Cohere MCP Server

Connect your Cohere account to any AI agent and leverage enterprise-grade AI models through natural conversation.

Mastra's agent abstraction provides a clean separation between LLM logic and Cohere tool infrastructure. Connect 6 tools through the Vinkius and use Mastra's built-in workflow engine to chain tool calls with conditional logic, retries, and parallel execution — deployable to any Node.js host in one command.

What you can do

Model Discovery — List all available Cohere models with their names, capabilities and context lengths
Chat API — Send conversations to Command models (command-r-plus, command-r, command-r7b) and receive responses with citations and tool call support
Embeddings — Generate vector embeddings for semantic search with multiple embedding types (float, int8, uint8, binary)
Reranking — Rerank documents by relevance to a search query using Cohere's industry-leading reranking models
Tokenization — Tokenize and detokenize text for estimating token counts and debugging

The Cohere MCP Server exposes 6 tools through the Vinkius. Connect it to Mastra AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Cohere to Mastra AI via MCP

Follow these steps to integrate the Cohere MCP Server with Mastra AI.

Install dependencies

Run npm install @mastra/core @mastra/mcp @ai-sdk/openai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.ts and run with npx tsx agent.ts

Explore tools

Mastra discovers 6 tools from Cohere via MCP

Why Use Mastra AI with the Cohere MCP Server

Mastra AI provides unique advantages when paired with Cohere through the Model Context Protocol.

Mastra's agent abstraction provides a clean separation between LLM logic and tool infrastructure — add Cohere without touching business code

Built-in workflow engine chains MCP tool calls with conditional logic, retries, and parallel execution for complex automation

TypeScript-native: full type inference for every Cohere tool response with IDE autocomplete and compile-time checks

One-command deployment to any Node.js host — Vercel, Railway, Fly.io, or your own infrastructure

Cohere + Mastra AI Use Cases

Practical scenarios where Mastra AI combined with the Cohere MCP Server delivers measurable value.

Automated workflows: build multi-step agents that query Cohere, process results, and trigger downstream actions in a typed pipeline

SaaS integrations: embed Cohere as a first-class tool in your product's AI features with Mastra's clean agent API

Background jobs: schedule Mastra agents to query Cohere on a cron and store results in your database automatically

Multi-agent systems: create specialist agents that collaborate using Cohere tools alongside other MCP servers

Cohere MCP Tools for Mastra AI (6)

These 6 tools become available when you connect Cohere to Mastra AI via MCP:

chat

Requires the model ID (e.g. "command-r-plus", "command-r", "command-r7b") and messages array in JSON format. Each message must have a "role" ("user", "assistant", "system" or "tool") and "content" (text or array of content blocks). Optionally set max_tokens, temperature (0-1), p (nucleus sampling 0-1) and tools array for function calling. Returns the model's response with text, citations and tool calls. Send a chat message to a Cohere model

detokenize

Requires the token IDs array. Returns the reconstructed text. Useful for debugging and verifying tokenization. Detokenize token IDs back to text using Cohere

embed

Requires the model ID (e.g. "embed-v4", "embed-v3"), texts array and input_type ("search_document", "search_query", "classification", "clustering"). Returns embedding vectors for each input text. Useful for semantic search, similarity comparison and vector database storage. Generate embeddings using Cohere

list_models

Each model returns its name (e.g. "command-r-plus", "command-r", "embed-v4", "rerank-v3.5"), endpoint compatibility, context length and tokenization info. Use this to discover which models are available and their capabilities. List all available Cohere models

rerank

Requires the model ID (e.g. "rerank-v3.5", "rerank-english-v3.0"), query text and documents array. Optionally set top_n to return only the top N results. Returns ranked documents with relevance scores. Rerank documents by relevance to a query

tokenize

Requires the text to tokenize and optionally the model. Returns the list of token IDs and token strings. Useful for estimating token counts before sending to chat or embed endpoints. Tokenize text using Cohere

Example Prompts for Cohere in Mastra AI

Ready-to-use prompts you can give your Mastra AI agent to start working with Cohere immediately.

"Send a message to Command R+ asking 'What is the capital of Brazil?'"

"Rerank these documents for the query 'machine learning models': ['Neural networks are inspired by biological neurons.', 'Python is a popular programming language.', 'Transformers use attention mechanisms for sequence processing.']"

"Generate embeddings for these texts: ['The weather is nice today.', 'I love programming in Python.'] using embed-v4."