How to Use the Cohere MCP in VS Code Copilot

Q: How do I share the Cohere MCP Server configuration with my team in VS Code Copilot?

Create a .vscode/mcp.json file in your repository root and add the server details. When team members open the project in VS Code 1.96 or higher, Copilot automatically loads the tools.

Q: Which Cohere models are supported by VS Code Copilot?

Any model returned by the listmodels tool is supported, including command-r-plus and rerank-v3.5. Copilot queries this list to match your prompt parameters with the correct endpoint.

Q: Can VS Code Copilot generate text embeddings using Cohere?

Yes, the embed tool allows Copilot to convert text strings into vector representations. This is highly useful when building local search features or vector database integrations in your project.

Equip VS Code Copilot with Cohere's enterprise-grade search, reranking, and generation models across your entire engineering team 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 VS Code Copilot

Create your Vinkius account to connect Cohere 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 with VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deploy Cohere tools to your team via VS Code Copilot

The `chat` tool connects VS Code Copilot to Cohere's Command models to generate code, draft documentation, and resolve errors. By committing the server settings to your `.vscode/mcp.json` file, every engineer on your team gets instant access to Cohere's models inside VS Code. This MCP tool returns precise citations and structural details, which VS Code Copilot uses to insert accurate code blocks directly into your workspace. It centralizes your Cohere model access without requiring separate API keys for every developer on the team.

Sort search results with enterprise reranking

The `rerank` tool lets your team sort massive document collections using Cohere's search engine directly from the VS Code Copilot chat window. Your VS Code agent calls this endpoint to filter out noisy search results and find the exact code references you need. This keeps your workspace clean and prevents VS Code Copilot from hitting context limits with irrelevant files. It brings Cohere's search optimization directly into your daily team-wide VS Code coding workflow.

Inspect token boundaries and model metadata

The `list_models` tool queries the active Cohere registry to show context limits and tokenization parameters for every endpoint inside VS Code Copilot. Your VS Code agent uses this information to select the best Cohere model for large codebase analyses. To prevent unexpected API errors, the `tokenize` tool checks the exact token count of your active file using Cohere's parser before sending it to VS Code Copilot. You can also use `detokenize` to inspect how specific code syntaxes are reconstructed by the Cohere engine.

Setup guide

Set up Cohere 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 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 tools listed. Try asking: "List my recent Cohere transactions" and Copilot will invoke them automatically.

.vscode/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 VS Code Copilot

Create a `.vscode/mcp.json` file in your repository root and add the server details. When team members open the project in VS Code 1.96 or higher, Copilot automatically loads the tools.

Any model returned by the `list_models` tool is supported, including command-r-plus and rerank-v3.5. Copilot queries this list to match your prompt parameters with the correct endpoint.

Yes, the `embed` tool allows Copilot to convert text strings into vector representations. This is highly useful when building local search features or vector database integrations in your project.

It runs through Vinkius's managed infrastructure, meaning your team only needs a single endpoint token to connect VS Code to the Cohere API securely.

Your text queries, document strings, and vector inputs are transmitted directly to Cohere's secure API. Vinkius processes these requests inside isolated, ephemeral execution environments, ensuring zero data persistence or logging of your proprietary codebases.

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