How to Use the GitGuardian MCP in Cursor

Q: How do I configure the GitGuardian MCP Server in Cursor?

Create a .cursor/mcp.json file in your project root and add the GitGuardian server configuration under the mcpServers key. Make sure your GGAPIKEY is set in your environment so the editor can authenticate your security queries.

Q: How does GitGuardian prevent duplicate alerts in Cursor?

The server uses bulkprefixlookup to check HMSL hashes of your keys against GitGuardian's database. This allows Cursor to verify if a secret has already been leaked and handled, preventing redundant alerts for known issues.

Q: Can I manage my GitGuardian team memberships from Cursor?

Yes. Your agent can run listteams and listteammemberships to check who has access to your security alerts. You can even run createteam to organize your developers directly from your editor.

Write secure code in Cursor by scanning for leaks and deploying honeytokens in real-time.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GitGuardian MCP to Cursor

Create your Vinkius account to connect GitGuardian to Cursor 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 GitGuardian with Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inline credential scanning inside Cursor

If the output of your build shows a raw key, you have a leak—and that's a problem. Let your Cursor agent run the MCP Server to scan your active file before you write it to disk. By calling `scan_content` directly from your editor tab, you catch hardcoded database passwords and private keys instantly. When your agent flags a leak, it doesn't just warn you. It can run `scan_and_create_incidents` to log the event in your workspace, ensuring every developer on your team maintains compliance without running manual CLI commands.

Automated incident response from the editor

When Cursor detects a security incident in your repository, ask the agent to run `list_secret_incidents` to fetch the details. You can view the severity, the affected file, and the leak history directly in the chat sidebar. Once you replace the leaked key with an environment variable, use `resolve_secret_incident` to mark the issue as fixed. If the alert is a false positive, run `ignore_secret_incident` to keep your workspace alert pipeline clean.

Active deception provisioning

Secure your codebases by generating decoy credentials directly within your Cursor workspace. Your agent can run the MCP Server to call `create_honeytoken` and place fake keys in your configuration files, setting a trap for any bad actor who gains access to your repository. Track these decoys by using `list_honeytoken_sources` to see exactly where they are deployed. If someone attempts to use one, your agent can run `list_honeytoken_events` to show you the intrusion details instantly.

Setup guide

Set up GitGuardian MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the GitGuardian MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent GitGuardian transactions." If the MCP tools are loaded correctly, Cursor will call the GitGuardian tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "gitguardian-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 GitGuardian. 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 GitGuardian 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 GitGuardian MCP in Cursor

Create a `.cursor/mcp.json` file in your project root and add the GitGuardian server configuration under the `mcpServers` key. Make sure your `GG_API_KEY` is set in your environment so the editor can authenticate your security queries.

Yes. If you have resolved a leak in your code, you can ask your Cursor agent to run `resolve_secret_incident` to close the alert. The agent will update the status on GitGuardian without requiring you to open an external web portal.

The server uses `bulk_prefix_lookup` to check HMSL hashes of your keys against GitGuardian's database. This allows Cursor to verify if a secret has already been leaked and handled, preventing redundant alerts for known issues.

Yes. Your agent can run `list_teams` and `list_team_memberships` to check who has access to your security alerts. You can even run `create_team` to organize your developers directly from your editor.

No. The Cursor MCP integration only sends the specific code blocks you scan via `scan_content` to GitGuardian's secure API. Your entire codebase is never uploaded, and all incident metadata is handled using industry-standard encryption protocols.

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