How to Use the Vald MCP in VS Code Copilot

Q: How do I get my team started using Vald in VS Code Copilot?

The best way is to commit the server definition into .vscode/mcp.json at the project root. This ensures every developer automatically gets access to all the tools provided by the Vald MCP Server.

Q: Can I audit data changes using VS Code Copilot and Vald?

You can monitor changes via updatevector or see what needs removal with deletevector. Since these actions are part of the shared config, they become visible to everyone on the team.

Q: What happens when I run a search query with Vald in VS Code Copilot?

The MCP Server executes searchvectors and sends the nearest neighbor results back. Copilot Chat uses this live data to provide context-aware suggestions, making your code accurate right out of the gate.

Standardize your team’s data access by committing Vald context via VS Code Copilot.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Vald MCP to VS Code Copilot

Create your Vinkius account to connect Vald 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 Vald with VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Provide Consistent Context Across Teams

Every developer on the team gets consistent results when you run a nearest neighbor search using `search_vectors`. By committing the configuration to `.vscode/mcp.json`, everyone uses the same Vald context. This ensures that whether it's a junior dev or a senior architect, they are all querying the central source of truth from your distributed vector engine.

Manage Team Knowledge Sources

The team can ensure its knowledge base is always current by committing updates. Use `update_vector` to change existing vectors and `insert_vector` to add new ones directly through the shared MCP Server configuration. If a data source becomes obsolete, use `delete_vector`. This makes managing institutional memory simple and visible within your Git workflow.

Validate System Readiness for New Hires

New team members can validate the system using `get_engine_info` before writing a line of code. You'll also need to check data structure requirements by calling `get_vector_details` with specific IDs. These tools confirm that the Vald MCP Server is fully operational and ready for enterprise development.

Setup guide

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

.vscode/mcp.json

{
  "mcpServers": {
    "vald-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 Vald. 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 Vald 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 Vald MCP in VS Code Copilot

The best way is to commit the server definition into `.vscode/mcp.json` at the project root. This ensures every developer automatically gets access to all the tools provided by the Vald MCP Server.

You can monitor changes via `update_vector` or see what needs removal with `delete_vector`. Since these actions are part of the shared config, they become visible to everyone on the team.

The MCP Server executes `search_vectors` and sends the nearest neighbor results back. Copilot Chat uses this live data to provide context-aware suggestions, making your code accurate right out of the gate.

Yes. By managing the MCP Server configuration in a committed file (`.vscode/mcp.json`), you're treating tool access like any other source code dependency, which is great for auditing.

This Vald MCP Server handles dense vectors. When committing configuration changes, you are defining how your team interacts with vector representations and associated metadata.

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