# Add the LinkedIn MCP to GitHub Copilot in VS Code

URL: https://zevari.ai/linkedin-mcp/vs-code

> Add the Zevari LinkedIn MCP to GitHub Copilot in VS Code with MCP: Add Server or one mcp.json entry, then sign in in your browser. Six specialists for LinkedIn and email. Every send waits for your approval until you switch a trained specialist to Autopilot.

VS Code LinkedIn MCP

To add a LinkedIn MCP to VS Code, run MCP: Add Server, choose HTTP and paste https://mcp.zevari.ai/mcp, then sign in to Zevari in your browser. Copilot gets Zevari's hosted LinkedIn and email tools: prospect search, ICP scoring, drafts in your voice, campaigns and reply triage. Nothing to install locally, no cookies, and every send waits for your approval until you switch a trained specialist to Autopilot.

[Start free trial](https://zevari.ai/auth/login?mode=signup&redirect=/app) See the steps

## VS Code

1. 1
  Add the server
  Open the Command Palette and run MCP: Add Server. Choose HTTP, paste the URL, enter zevari as the server ID, then choose Global so it is available in every workspace.
  ```
  https://mcp.zevari.ai/mcp
  ```
2. 2
  Or add it to a workspace file
  To share it with one project, put this in .vscode/mcp.json instead. VS Code uses the servers key here, not mcpServers.
  ```
  { "servers": { "zevari": { "type": "http", "url": "https://mcp.zevari.ai/mcp" } } }
  ```
3. 3
  Sign in
  When the server first starts, VS Code opens the Zevari sign-in in your browser. Review the prompt, sign in and approve access.
4. 4
  Check the connection
  Open Copilot Chat in agent mode, check that the Zevari tools are turned on in the tools list, then ask:
  ```
  Use Zevari to show my available workspaces and LinkedIn senders.
  ```

Does setup differ per client?

## What is different about VS Code

Every client reaches the same hosted server at https://mcp.zevari.ai/mcp and signs in the same way: you sign in to Zevari in your browser and approve access. The tools and the approval rules are identical. Only where you add the server, and how the sign-in starts, changes.

- VS Code's mcp.json uses a servers key and needs "type": "http" next to the URL. Files written for Cursor or Claude use mcpServers and will not work as they are.
- MCP tools run in Copilot's agent mode, and you can turn each Zevari tool on or off in the tools list.
- If your GitHub organization or enterprise manages Copilot, an admin must allow MCP servers in Copilot, and may need to add mcp.zevari.ai to its allowlist.
- The tools, the approval rules and the Zevari account are the same as in Claude, ChatGPT and Codex.

| Client | Where you add Zevari | How you sign in | Guide |
| --- | --- | --- | --- |
| Claude.ai and Claude Desktop | Customize → Connectors → Add custom connector. Name Zevari AI, URL https://mcp.zevari.ai/mcp | When Claude asks, sign in to Zevari in your browser and approve access. On Team and Enterprise an Owner adds the connector first | [Guide](https://zevari.ai/linkedin-mcp/claude) |
| Claude Code | claude mcp add --transport http zevari https://mcp.zevari.ai/mcp | Run /mcp inside Claude Code, pick zevari, sign in in the browser | [Guide](https://zevari.ai/linkedin-mcp/claude) |
| Claude Cowork | The same custom connector as Claude.ai. Connectors added to your Claude account are available in Cowork | Sign in once when you add the connector, then turn Zevari on from the + menu in a Cowork task | [Guide](https://zevari.ai/linkedin-mcp/claude-cowork) |
| ChatGPT | Personal plans: Developer mode under Settings → Apps → Advanced, then Create. Business, Enterprise, Edu: an admin or owner creates it under Workspace Settings → Apps | ChatGPT opens the Zevari sign-in in your browser. Workspace members connect once an admin has created the app | [Guide](https://zevari.ai/linkedin-mcp/chatgpt) |
| Codex CLI | codex mcp add zevari --url https://mcp.zevari.ai/mcp | Codex does not start the sign-in on its own. Run codex mcp login zevari | [Guide](https://zevari.ai/linkedin-mcp/codex) |
| Cursor | One-click install link, or add zevari with the URL https://mcp.zevari.ai/mcp to ~/.cursor/mcp.json | Cursor opens the Zevari sign-in in your browser. In the Cursor CLI, run agent mcp login zevari | [Guide](https://zevari.ai/linkedin-mcp/cursor) |
| Gemini app and Gemini CLI | Gemini app: Settings → Connected Apps → Custom apps, paste the URL. Gemini CLI: gemini mcp add --transport http --scope user zevari https://mcp.zevari.ai/mcp | Both open the Zevari sign-in in your browser. In Gemini CLI, run /mcp auth zevari to sign in again | [Guide](https://zevari.ai/linkedin-mcp/gemini) |
| Perplexity | Plugins → Add custom → Connector → Add MCP connector → Remote, with OAuth and Streamable HTTP | Click the Zevari card to sign in. On Enterprise, an admin must allow members to add custom connectors | [Guide](https://zevari.ai/linkedin-mcp/perplexity) |
| VS Code with GitHub Copilot | MCP: Add Server → HTTP, paste the URL, or add zevari to .vscode/mcp.json | When the server first starts, VS Code opens the Zevari sign-in in your browser | This page |
| Other MCP clients | Add https://mcp.zevari.ai/mcp as a remote (HTTP) MCP server | Browser sign-in, or an MCP access token from Settings → Developers for clients that cannot open a browser | [Guide](https://zevari.ai/linkedin-mcp#clients) |

Once it is connected

## Your AI gets a full outbound department for LinkedIn and email

Your AI SDR team for LinkedIn and email: six specialists your AI can hand work to, in plain English. Start with this check in a new chat:

```
Use Zevari to show my available workspaces and LinkedIn senders.
```

### Prospecting

Finds people from a plain-English description and fills the contact record, including a verified email.

### Signals

Watches for reasons to reach out, like a post about the problem you solve, and ranks them.

### ICP Scoring

Scores each lead against your ideal customer profile, with written reasons.

### Voice Writer

Drafts connection notes, messages and emails that sound like you.

### Follow-up

Runs the sequence across LinkedIn and email on your working hours.

### Reply Qualifier

Reads replies and flags the qualified conversations worth your time.

The full list is on [what the LinkedIn MCP can do](https://zevari.ai/linkedin-mcp/tools), and there are ready-made [LinkedIn MCP prompts](https://zevari.ai/linkedin-mcp/prompts) to copy.

## Nothing sends until you approve it

Your AI stages the work and you approve each send, unless you have moved a specialist to autopilot after it earned it. Zevari holds every account to enforced limits: 100 connection requests a week on Free*, 150 on Premium, 200 on Sales Navigator, a daily cap on all actions, burst limits, and your working hours. No browser extension, no cookie injection. The weekly figure covers connection requests sent without a note: LinkedIn caps requests that carry a note at 3 a month on a free account, and gives Premium and Sales Navigator a far larger allowance, so Premium or Sales Navigator is the practical choice for real outbound (see /safety).

[Read the safety model](https://zevari.ai/safety)

Troubleshooting

## If Zevari does not show up

### zevari does not start

Check that the entry has "type": "http" and sits under servers. Then run MCP: List Servers, pick zevari and start it.

### VS Code asks for a client ID

You do not need one. Zevari registers VS Code automatically during sign-in. Cancel, restart the server and complete the browser sign-in.

### Copilot has no MCP tools at work

Your organization has MCP servers in Copilot turned off or limited to an allowlist. Ask your GitHub admin to allow mcp.zevari.ai.

### Tools answer that a funded LinkedIn seat is needed

You can connect before paying, but Zevari tools only run in a workspace with a funded LinkedIn seat. Add or associate one in Billing, then ask again.

FAQ

## VS Code LinkedIn MCP questions

### Is there a LinkedIn MCP for VS Code?

Yes. Zevari is a hosted LinkedIn MCP server that GitHub Copilot in VS Code connects to at https://mcp.zevari.ai/mcp. Once you sign in, Copilot can find and score prospects, draft messages and run campaigns on LinkedIn and email, with every send waiting for your approval.

### Can Copilot send LinkedIn messages on its own?

No. Copilot can research, draft and stage messages, connection requests and posts, but each send waits for your approval unless you have moved a specialist to autopilot, and Zevari enforces weekly and daily limits on the account.

### Is setup the same as Cursor?

The server and the sign-in are the same. The file is not: VS Code uses servers with "type": "http", while Cursor uses mcpServers.

### Is Zevari affiliated with Microsoft or GitHub?

No. Zevari is independent and is not affiliated with, endorsed by, or sponsored by Microsoft or GitHub.

### Does every send need my approval?

Yes, by default. Your AI can research, score and draft, but every message, connection request, comment and post waits for your approval. The only exception is a specialist you have moved to autopilot yourself, after it has earned it (for Follow-up, ten approved sends in 30 days). Switch it back to reviews with you at any time.

### Do I need a browser extension or my LinkedIn cookies?

No. Zevari is a hosted connector. There is no browser extension, no cookie injection and nothing to keep open on your computer.

### What does it cost?

Operator is $87/mo, or $497/yr (save 52%). The MCP connection is included, along with all six specialists for LinkedIn and email. Another LinkedIn account is $37 a month.

### Is Zevari affiliated with LinkedIn?

No. Zevari is independent and is not affiliated with, endorsed by, or sponsored by LinkedIn Corporation. LinkedIn is a trademark of LinkedIn Corporation.

## A full outbound department, running today.

Your AI SDR team for LinkedIn and email, working from the AI client you already use. $87/mo, or $497/yr (save 52%).

[Start free trial](https://zevari.ai/auth/login?mode=signup&redirect=/app) [See pricing](https://zevari.ai/pricing)

[LinkedIn MCP for Cursor One install link or one mcp.json entry.](https://zevari.ai/linkedin-mcp/cursor) [LinkedIn MCP for Codex Two commands: codex mcp add, then codex mcp login.](https://zevari.ai/linkedin-mcp/codex) [LinkedIn MCP for Claude Custom connector in Claude, or one command in Claude Code.](https://zevari.ai/linkedin-mcp/claude) [LinkedIn MCP prompts Prompts to paste into Copilot once it is connected.](https://zevari.ai/linkedin-mcp/prompts)