An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect GitGuardian to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Stop credential leaks and manage security incidents through your AI agent.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 49 capabilities

We ship only the actions that matter.

Capability set01 / 13

01-04

4 capabilities in this set.

Part of 49 available through GitGuardian.

  1. 01

    Get self API token

    This capability retrieves the details for your current API token.

  2. 02

    List sources

    Use this to get a list of all connected sources.

  3. 03

    Resolve secret incident

    This capability marks a specific secret incident as resolved.

  4. 04

    Revoke honeytoken

    Use this to immediately revoke a honeytoken.

Capability set02 / 13

05-08

4 capabilities in this set.

Part of 49 available through GitGuardian.

  1. 05

    Ignore secret incident

    This capability allows you to ignore a specific secret incident.

  2. 06

    List audit log event names

    This capability provides a list of all existing event names for your audit logs.

  3. 07

    List custom tags

    Use this to see all your custom tags.

  4. 08

    List health check history

    This capability retrieves the health check history for a specific instance.

Capability set03 / 13

09-12

4 capabilities in this set.

Part of 49 available through GitGuardian.

  1. 09

    List honeytoken events

    Use this to view all events related to your honeytokens.

  2. 10

    List honeytoken notes

    This capability retrieves all notes associated with honeytokens.

  3. 11

    List honeytoken sources

    Use this to find which sources a honeytoken has appeared in.

  4. 12

    List ips

    This capability lists the IP addresses used by GitGuardian.

Capability set04 / 13

13-16

4 capabilities in this set.

Part of 49 available through GitGuardian.

  1. 13

    List members

    Use this to see the members in your workspace.

  2. 14

    List scim groups

    This capability lists groups via SCIM.

  3. 15

    List scim users

    Use this to list members via SCIM.

  4. 16

    List teams

    This capability provides a list of your teams.

Capability set05 / 13

17-20

4 capabilities in this set.

Part of 49 available through GitGuardian.

  1. 17

    Multiscan content

    Use this to scan multiple pieces of content for secrets at once.

  2. 18

    Reset honeytoken

    This capability resets a honeytoken.

  3. 19

    Revoke self API token

    Use this to revoke your current API token.

  4. 20

    Scan and create incidents

    This capability scans content and automatically generates incidents if secrets are found.

Capability set06 / 13

21-24

4 capabilities in this set.

Part of 49 available through GitGuardian.

  1. 21

    Create honeytoken

    Use this to generate a new honeytoken.

  2. 22

    Create honeytoken with context

    This capability creates a honeytoken within a specific context.

  3. 23

    Delete custom tag

    Use this to remove a custom tag.

  4. 24

    Create team

    This capability allows you to create a new team.

Capability set07 / 13

25-28

4 capabilities in this set.

Part of 49 available through GitGuardian.

  1. 25

    Delete custom tags key

    Use this to delete a custom tags key.

  2. 26

    Get custom tag

    This capability retrieves the details of a custom tag.

  3. 27

    Get health

    Use this to check the current API health status.

  4. 28

    Get honeytoken

    This capability retrieves information about a specific honeytoken.

Capability set08 / 13

29-32

4 capabilities in this set.

Part of 49 available through GitGuardian.

  1. 29

    Get quotas

    Use this to check your current quota overview.

  2. 30

    Bulk prefix lookup

    This capability performs a bulk lookup for honeytoken HMSL hashes.

  3. 31

    Create custom tag

    Use this to add a new custom tag.

  4. 32

    Trigger source scans

    This capability triggers new scans on your sources.

Capability set09 / 13

33-36

4 capabilities in this set.

Part of 49 available through GitGuardian.

  1. 33

    Update custom tag full

    Use this to perform a full update of a custom tag.

  2. 34

    Update custom tag partial

    This capability allows for a partial update of a custom tag.

  3. 35

    Update custom tags key

    Use this to update a custom tags key.

  4. 36

    Update secret incident

    This capability lets you update the details of a secret incident.

Capability set10 / 13

37-40

4 capabilities in this set.

Part of 49 available through GitGuardian.

  1. 37

    Assign secret incident

    Use this to assign a secret incident to a team member.

  2. 38

    Create honeytoken note

    This capability allows you to add a note to a honeytoken.

  3. 39

    Get secret incident

    Use this to retrieve details for a specific secret incident.

  4. 40

    List API tokens

    This capability lists all your API tokens.

Capability set11 / 13

41-43

3 capabilities in this set.

Part of 49 available through GitGuardian.

  1. 41

    List audit logs

    Use this to view the audit logs for your workspace.

  2. 42

    List health checks

    This capability retrieves a list of health checks.

  3. 43

    List honeytokens

    Use this to see all your honeytokens.

Capability set12 / 13

44-46

3 capabilities in this set.

Part of 49 available through GitGuardian.

  1. 44

    List ip allowlist

    This capability lists your current IP allowlist rules.

  2. 45

    List secret incidents

    Use this to view all secret incidents.

  3. 46

    List team memberships

    This capability lists the members of your teams.

Capability set13 / 13

47-49

3 capabilities in this set.

Part of 49 available through GitGuardian.

  1. 47

    Scan content

    Use this to scan a specific piece of content for secrets.

  2. 48

    Trigger health check

    This capability triggers a new health check.

  3. 49

    Update honeytoken

    Use this to update the details of a honeytoken.

Real work

What teams actually run

01

Rapid Incident Triage

When a leak is detected, use your agent to quickly identify the source and assign it to a responder.

02

Proactive Code Scanning

Before pushing code, ask your agent to scan a snippet to ensure no credentials are being exposed.

03

Deceptive Defense

Deploy honeytokens into your infrastructure to catch attackers attempting to use stolen credentials.

04

Compliance Monitoring

Review audit logs and workspace activity to maintain security policy standards.

Automate a task

Put GitGuardian to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

GitGuardian works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put GitGuardian to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

1273ms average. Fast in production.

GitGuardian is checked daily against the live service.

Daily averagePeak 1508ms
Oct 3Today
Fastest day
959ms
Slowest day
1508ms
14-day trend
Stable-4%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 49 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of GitGuardian, so you can see the experience inside your AI.

It does not authenticate your account with GitGuardian. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

GitGuardian Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_NQtV8WXJZTZDwZLKUu4JIzBlR9PvO6RL6VjurLD6/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — GitGuardian capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "gitguardian-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_NQtV8WXJZTZDwZLKUu4JIzBlR9PvO6RL6VjurLD6/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up GitGuardian in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work GitGuardian owners hand off.

Security and DevOps professionals who need to manage secrets without leaving their primary development environment.

  • 01

    Security Engineers

    They use the agent to triage incidents and deploy honeytokens across environments.

  • 02

    DevOps & SREs

    They automate security audits and monitor workspace health from their IDE.

  • 03

    Developers

    They scan code for secrets and check incident status without opening a browser.

FAQ

Questions GitGuardian owners ask.

  • 01

    How do I connect GitGuardian to my AI client?

    Subscribe to the MCP on Vinkius and enter your GitGuardian API Key. Once connected, you can use it immediately in Claude, Cursor, or Windsurf.

  • 02

    Can I use this to scan code before I commit it?

    Yes. You can pass code snippets directly to your agent and ask it to scan for secrets using the available scanning capabilities.

  • 03

    What are honeytokens and can I manage them here?

    Honeytokens are decoy credentials used to detect intruders. This MCP allows you to create, list, update, and revoke them through your AI agent.

  • 04

    Does this replace the GitGuardian dashboard?

    It doesn't replace it, but it acts as a powerful interface for common tasks like triaging incidents and managing teams directly from your workflow.

  • 05

    Is my API key secure?

    Vinkius manages your credentials and keeps the connection running securely so you don't have to handle the underlying infrastructure.

  • 06

    Can I resolve a secret incident directly through the AI?

    Yes. You can use the resolve_secret_incident capability by providing the incident ID. You can also use assign_secret_incident to delegate the fix to a specific team member.

  • 07

    How do I create a decoy credential to catch attackers?

    Use the create_honeytoken capability. You can specify the type and name of the honeytoken, and GitGuardian will generate a decoy that alerts you if it's ever used.

  • 08

    Is it possible to scan a text block for secrets before I commit it?

    Absolutely. Use the scan_content capability. Provide the document content and a filename, and the AI will return any detected secrets or policy violations found by GitGuardian's engine.

Explore

More in Fort Knox

Suggestions

Connect GitGuardian to Claude, Cursor, ChatGPT & more