How to Use the Cohere MCP in Windsurf

Q: How does Cohere reranking work inside Windsurf?

You pass a query and a list of documents to the rerank tool. Windsurf then receives the sorted results based on semantic relevance. It helps your agent prioritize the most useful code context.

Q: Can I use Cohere for embeddings in Windsurf?

Yes, the embed tool generates vectors for your text snippets. You can store these in a database and let Windsurf perform semantic searches across your codebase.

Q: Does this MCP Server support Windsurf model discovery?

The listmodels tool fetches every available Cohere model ID and its current context limit. You can see exactly what version you are using inside your IDE session.

Q: How do I add the Cohere MCP Server to Windsurf?

Open your mcpconfig.json file or use the built-in MCP settings UI in Windsurf. Add the server entry and click refresh to start using the tools immediately.

Connect Cohere to Windsurf for direct model access and document reranking inside your IDE.

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 Windsurf

Create your Vinkius account to connect Cohere to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Direct model chat in Windsurf

Trigger the `chat` tool to pipe prompts from Cascade directly into Command R Plus. It handles your message history and tool calls, so you get raw model output without leaving your editor. Since Windsurf manages the context, you can feed code blocks into the model and get back precise edits. It keeps your workflow inside the IDE rather than switching to a browser.

Rerank project docs with Windsurf

Use `rerank` to sort your local documentation or search results by relevance. Cascade can pull specific files and order them based on how well they match your current coding task. This saves you from digging through irrelevant documentation when you need a specific API signature. It turns your scattered project knowledge into a structured list that Windsurf can actually use.

Manage tokens for Windsurf

Run `tokenize` or `detokenize` to see exactly how your text hits the model's limits. This is vital when you are pushing large context windows through the IDE. Check your counts before you commit to a long prompt. It prevents those annoying mid-request failures and keeps your agent operations within the model's constraints.

Setup guide

Set up Cohere MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the Cohere MCP

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

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Cohere payment history." If connected, Cascade will call the Cohere tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.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 Windsurf

You pass a query and a list of documents to the `rerank` tool. Windsurf then receives the sorted results based on semantic relevance. It helps your agent prioritize the most useful code context.

Yes, the `embed` tool generates vectors for your text snippets. You can store these in a database and let Windsurf perform semantic searches across your codebase.

The `list_models` tool fetches every available Cohere model ID and its current context limit. You can see exactly what version you are using inside your IDE session.

This server only sends the text you explicitly provide in your tool calls to the API. Your local codebase remains on your machine; only the snippets sent to the `chat` or `embed` tools leave your environment.

Open your mcp_config.json file or use the built-in MCP settings UI in Windsurf. Add the server entry and click refresh to start using the tools immediately.

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