How to Use the Cohere (AI Platform) MCP in Windsurf

Q: Can Windsurf use Cohere (AI Platform) to rank my local project files?

Yes. Cascade reads your local files, passes them to the rerankdocuments tool, and uses the returned order to decide which files to edit first.

Q: Does Windsurf support custom model selection with Cohere (AI Platform)?

Yes. Cascade queries the listmodels tool to identify available models and automatically selects the correct one for your task.

Q: How do I handle large token limits when sending code to this server?

Cascade uses tokenizetext to split your code into safe chunks before sending them to the API. This avoids hitting payload size limits during long generation tasks.

Run multi-step Cohere generation and document reranking workflows autonomously inside Windsurf.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cohere (AI Platform) MCP to Windsurf

Create your Vinkius account to connect Cohere (AI Platform) 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 (AI Platform) with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Smart document reranking with Windsurf Cascade

The `rerank_documents` tool lets Cascade sort search results by relevance without making you prompt each step. Cascade takes a user query, grabs raw text, and feeds it into the Cohere rerank model to find the most relevant chunks immediately. Because Windsurf handles multi-step chains on its own, it uses this MCP Server to check available endpoints before selecting the best model for the job. This keeps your agent running without hitting missing endpoint errors.

Multi-step text classification via Windsurf

The `classify_inputs` tool evaluates your workspace strings against static categories to tag files or sort incoming data. Cascade initiates this classification, reads the output, and immediately organizes your files based on the returned classes. If the text is too long, Cascade uses `tokenize_text` to check the exact NLP limits before running the classification. This prevents API errors and keeps the autonomous workflow running smoothly in this MCP Server.

Run Cohere chat generation in Windsurf

The `chat_generation` tool executes explicitly formatted conversational transformations directly inside your workspace. Cascade uses this to rewrite code comments, draft documentation, or refactor code blocks based on your prompt. When Cascade needs to generate fresh code files, it runs `generate_text` to write raw blocks based on your workspace context. You get clean code written by Cohere models without having to copy-paste anything.

Setup guide

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

mcp_config.json

{
  "mcpServers": {
    "cohere-ai-platform-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 (AI Platform) 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 (AI Platform) MCP in Windsurf

Windsurf connects to this MCP server via your configuration file. Once active, Cascade calls tools like `chat_generation` or `rerank_documents` autonomously during its multi-step planning.

Yes. Cascade reads your local files, passes them to the `rerank_documents` tool, and uses the returned order to decide which files to edit first.

Yes. Cascade queries the `list_models` tool to identify available models and automatically selects the correct one for your task.

Cascade uses `tokenize_text` to split your code into safe chunks before sending them to the API. This avoids hitting payload size limits during long generation tasks.

Your workspace text and documents go directly to Cohere's API endpoints for processing. Vinkius runs the server in an isolated sandbox, meaning your raw inputs are never logged or stored on our platform.

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