How to Use the Cohere MCP in Claude

Q: How do I configure this Cohere MCP Server with Claude Desktop?

Open your local claudedesktopconfig.json file and add the server configuration under the mcpServers key. Alternatively, paste the Vinkius remote connection URL directly into the integrations page on claude.ai.

Q: Which Cohere models can I run through Claude Desktop?

You can query any model returned by the listmodels tool, including command-r-plus, command-r, and embed-v4. The chat tool handles the execution and passes the model parameters directly.

Q: Do I need to manage Python dependencies for tokenization?

No, you do not need local packages. The tokenize and detokenize tools run directly through the API, letting your agent inspect token counts without local runtime setups.

Give Claude Desktop direct access to Cohere's Command models, reranking engine, and text embeddings via MCP.

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 Claude Desktop

Create your Vinkius account to connect Cohere to Claude Desktop 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 Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Cohere models directly inside Claude Desktop using MCP

The `chat` tool lets you route prompts directly to Cohere Command models like command-r-plus from your Claude Desktop chat window. Your agent calls this tool to get raw text, citation arrays, and structured tool responses back in your active chat thread. You can switch between active Cohere endpoints on the fly by calling `list_models` to check which versions are currently available in your Claude Desktop config. This MCP setup runs locally via stdio or connects through a remote custom connector in your browser settings.

Sort search results with native document reranking

The `rerank` tool evaluates a list of documents against a specific query using Cohere's ranking engine to return relevance scores inside Claude Desktop. Your agent uses this to filter down massive text dumps before pasting them into your main Claude window. By feeding only the most relevant Cohere hits into your context window, you save on token usage. It turns a messy pile of raw search results into a clean, ordered list right inside your active Claude Desktop workspace.

Analyze token counts and embeddings on the fly

The `tokenize` tool breaks down your input text into token IDs and strings so you can inspect how Cohere processes your prompts inside Claude Desktop. If you need to reverse the process, the `detokenize` tool converts those raw IDs back into readable text directly in your active Claude thread. For semantic search tasks, the `embed` tool generates high-dimensional vectors from your text inputs using Cohere's embed-v4 model. This lets you inspect raw vector data or test clustering logic without opening a separate terminal outside of Claude Desktop.

Setup guide

Set up Cohere MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Cohere MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Cohere MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under cohere-mcp.

json

{
  "mcpServers": {
    "cohere-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Claude Desktop

Open your local `claude_desktop_config.json` file and add the server configuration under the `mcpServers` key. Alternatively, paste the Vinkius remote connection URL directly into the integrations page on claude.ai.

You can query any model returned by the `list_models` tool, including command-r-plus, command-r, and embed-v4. The `chat` tool handles the execution and passes the model parameters directly.

Yes, you can pass a list of documents and a search query directly to the `rerank` tool. Your agent will analyze the resulting scores to prioritize the most relevant data in your chat window.

No, you do not need local packages. The `tokenize` and `detokenize` tools run directly through the API, letting your agent inspect token counts without local runtime setups.

Every text string, document list, and token array processed by the `chat` or `embed` tools goes directly to Cohere via secure V8 sandboxed isolates. Vinkius never logs or retains the raw payloads, ensuring your proprietary documents remain completely ephemeral.

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