How to Use the Salesforce MCP in VS Code Copilot

Q: How can my team use VS Code Copilot to find all open opportunities in Salesforce?

Any developer can just ask Copilot to run a soqlquery like "SELECT Name, StageName FROM Opportunity WHERE IsClosed = false". The agent will execute it and return the results directly in the chat panel.

Q: Is it possible to use different Salesforce orgs for different projects?

Yes. Because the configuration can live in the project's .vscode/mcp.json file, your team can have one project connected to production and another connected to a sandbox, each with its own settings.

Equip your entire engineering team with Salesforce tools inside VS Code. Shared config, consistent results.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Salesforce MCP to VS Code Copilot

Create your Vinkius account to connect Salesforce to VS Code Copilot — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Salesforce with VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Standardize Salesforce Access for Your Team

Check `.vscode/mcp.json` into your repository, and every developer on the team gets the same set of Salesforce tools instantly. This ends the "it works on my machine" problem for good. This is a proper MCP setup for a team. New engineers can pull the repo and immediately ask Copilot to `get_record` or `run_report` without any manual configuration. It makes onboarding faster and guarantees everyone is building against the same API definitions.

Query and Change Records in VS Code

Your team can now use Copilot to run a `soql_query` and get back live data from your org right in their editor. It’s perfect for debugging a problem or scaffolding a new feature that depends on CRM data. This MCP server connects your agent to more than just read operations. Copilot can use `create_record` to add a new Case, `update_record` to change an Opportunity's status, or even `delete_record` in a test environment. It's full CRM interaction without leaving VS Code.

A Salesforce MCP Server for Copilot

This gives Copilot real agency. Your AI assistant isn't just suggesting code anymore; it's interacting with your company's most critical data source. It can perform a `global_search` for a customer or `list_accounts` to get context for a new feature. This MCP server makes Copilot a true partner in development. It can fetch object schemas with `describe_object` to help write validation logic, or pull a list of active reports with `list_reports` for an admin dashboard you're building.

Setup guide

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

.vscode/mcp.json

{
  "mcpServers": {
    "salesforce-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 Salesforce. 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 Salesforce 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 Salesforce MCP in VS Code Copilot

Any developer can just ask Copilot to run a `soql_query` like "SELECT Name, StageName FROM Opportunity WHERE IsClosed = false". The agent will execute it and return the results directly in the chat panel.

Yes. Paste a list of names and companies into the chat and instruct Copilot to iterate through them, calling `create_record` for each one. It will create the new Contact records in Salesforce.

You don't have to. The tools are dynamic. Just ask Copilot to run `describe_object` on the object that changed, and it will fetch the new metadata from Salesforce in real-time.

Yes. Because the configuration can live in the project's `.vscode/mcp.json` file, your team can have one project connected to production and another connected to a sandbox, each with its own settings.

The server is a pass-through. It uses your team's provided authentication to make secure API calls to Salesforce. All data in transit, including Account and Contact records, is encrypted, and Vinkius infrastructure never inspects or retains any of your CRM data payloads.

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