How to Use the Cohere (AI Platform) MCP in VS Code Copilot

Q: How do we roll out the Cohere (AI Platform) MCP Server to our entire team in VS Code Copilot?

Create a .vscode/mcp.json file in your repository's root directory and commit it. When your developers open the project in VS Code Copilot, the editor automatically loads the MCP Server configuration.

Q: Can VS Code Copilot use the Cohere (AI Platform) classification tool for log analysis?

Yes, Copilot can call classifyinputs to analyze and map log strings to static classes. This helps your team quickly categorize error patterns or system events directly from the chat panel.

Equip your VS Code Copilot team with Cohere's classification and document reranking tools via a shared config.

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 VS Code Copilot

Create your Vinkius account to connect Cohere (AI Platform) to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Share Cohere tools across your team in VS Code Copilot

Stop forcing every engineer to configure their own environment. By committing a `.vscode/mcp.json` file to your repo, your entire team instantly gets access to this MCP Server inside VS Code Copilot. Your developers can immediately run `chat_generation` and `generate_text` to draft code or documentation. Copilot handles the API calls in the background, keeping everyone on the same page.

Reorder massive documentation sets inside the editor

When your team is working with huge codebases, VS Code Copilot uses `rerank_documents` to clean up the search noise. It takes a list of document chunks and reorders them so the agent only reads what is actually relevant. This saves your team from burning through token limits. Copilot gets the structured routing arrays and ignores the junk, making your codebase searches incredibly precise.

Embed and classify strings during development

This MCP Server lets VS Code Copilot run `generate_embeddings` to build dense vectors for your local search tools. You can test your vector-based search features using real production-grade embeddings right inside the editor. If you need to sort logs or user inputs, Copilot calls `classify_inputs` to evaluate strings against static limits. It can also run `tokenize_text` to check structural boundaries before committing code.

Setup guide

Set up Cohere (AI Platform) MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Cohere (AI Platform) MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Cohere (AI Platform) tools listed. Try asking: "List my recent Cohere (AI Platform) transactions" and Copilot will invoke them automatically.

.vscode/mcp.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 VS Code Copilot

Create a `.vscode/mcp.json` file in your repository's root directory and commit it. When your developers open the project in VS Code Copilot, the editor automatically loads the MCP Server configuration.

Yes, Copilot can call `classify_inputs` to analyze and map log strings to static classes. This helps your team quickly categorize error patterns or system events directly from the chat panel.

No, because Vinkius manages the hosting and authentication. You set up the subscription once, and your team connects to the server using a single secure endpoint token within VS Code Copilot.

You need VS Code version 1.96 or higher. Once updated, you can switch Copilot Chat to Agent mode to let it invoke the text generation and reranking tools.

All codebase snippets, text inputs, and embeddings are processed through ephemeral V8 isolates. No data is stored on Vinkius, and everything is sent securely to the Cohere API without touching third-party logs.

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