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

Q: How does Windsurf use Cohere (Embed & Rerank) to improve search accuracy?

Cascade calls embedtexts to generate vector representations of your files and queries. After that, it executes rerankdocuments to ensure the most relevant code chunks are prioritized during its planning phase. This stops the agent from getting distracted by unrelated files.

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

The tool uses listmodels to query the Cohere API directly. This lets your agent check active endpoints and pick the best one for embedding or classification tasks dynamically.

Give Windsurf's Cascade the power to vector-search and rerank your codebase context on its own.

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 Windsurf

Create your Vinkius account to connect Cohere (Embed & Rerank) 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 (Embed & Rerank) with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Cascade-driven semantic search with Cohere

You don't have to manually hunt for relevant code snippets when you're working on a massive refactor. Cascade uses `embed_texts` to turn your query into dense vectors, letting it hunt down the exact semantic match across your codebase. This isn't basic keyword matching; it actually understands what your functions are trying to do. Once it grabs those matches, Cascade runs `rerank_documents` to sort the results, putting the most critical context right at the top. The agent builds its own execution plan, grabbing the right files and ignoring the noise before it writes a single line of code.

Automated text classification in your editor

Sorting raw input data gets tedious fast. By hooking this MCP Server up to Windsurf, you let Cascade organize unstructured text, logs, or user feedback without leaving the IDE. The agent invokes `classify_texts` to map strings into predefined buckets, saving you from writing messy regex or custom parsing scripts. Simply tell Cascade what categories you care about. It checks the API limits, maps the text, and writes the sorted output directly back into your workspace files.

Precise context optimization for Windsurf

Large files can easily blow past token limits and waste your budget. Cascade handles this by calling `tokenize_text` to check the exact structural segmentation of your files before sending them off. You get precise control over your prompt windows without guessing how much data is going through. If you need to swap models or check what's currently active, the agent uses `list_models` to inspect the available Cohere endpoints. It adjusts its plan on the fly based on what's online, keeping your automated steps running smoothly.

Setup guide

Set up Cohere (Embed & Rerank) 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 (Embed & Rerank) 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 (Embed & Rerank) payment history." If connected, Cascade will call the Cohere (Embed & Rerank) tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "cohere-embed-rerank-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 (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 Windsurf

Cascade calls `embed_texts` to generate vector representations of your files and queries. After that, it executes `rerank_documents` to ensure the most relevant code chunks are prioritized during its planning phase. This stops the agent from getting distracted by unrelated files.

Yes, Windsurf's Cascade agent runs these tools in sequence without needing your permission for every step. It can analyze a file, run `classify_texts` to categorize the content, and save the results automatically. You just set the initial goal and let the agent work.

Setting it up takes less than a minute. You can paste the connection details directly into your configuration under the `mcpServers` key to register the MCP Server. Once saved, Cascade immediately detects the new capabilities and starts using them.

The tool uses `list_models` to query the Cohere API directly. This lets your agent check active endpoints and pick the best one for embedding or classification tasks dynamically.

Your raw text, document chunks, and queries are sent directly to Cohere's API via secure HTTPS. Vinkius runs the server in an isolated V8 sandbox, meaning your raw inputs are never cached, stored, or logged on our infrastructure. Everything stays 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