Bring Secret Detection
to Cursor
Learn how to connect GitGuardian to Cursor and start using 49 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for SubscribersCompatible with every major AI agent and IDE
Gemini
What is the GitGuardian MCP Server?
Connect your GitGuardian workspace to any AI agent to strengthen your security posture and manage secret leaks through natural conversation.
What you can do
- Incident Management — List, retrieve, and resolve secret incidents. Assign team members to leaks and track remediation progress.
- Honeytokens — Create and manage decoy credentials (honeytokens) to detect unauthorized access to your private infrastructure.
- Security Scanning — Scan code snippets or content for secrets and sensitive data in real-time to prevent leaks before they happen.
- Audit & Compliance — Access detailed audit logs to monitor workspace activity and ensure compliance with security policies.
- Team Collaboration — Manage teams, members, and API tokens to orchestrate security operations across your organization.
How it works
- Subscribe to this server
- Enter your GitGuardian API Key
- Start monitoring and securing your code from Claude, Cursor, or any MCP-compatible client
Your AI acts as a 24/7 Security Operations Center (SOC) assistant, helping you triage alerts and deploy defenses without leaving your workflow.
Who is this for?
- Security Engineers — quickly triage secret incidents and manage honeytoken deployments across multiple environments.
- DevOps & SREs — automate security audits and monitor workspace health checks directly from the terminal or IDE.
- Developers — scan code for secrets before committing and check incident statuses without switching to the GitGuardian dashboard.
Built-in capabilities (49)
Assign a secret incident
Bulk lookup for honeytoken HMSL hashes
Create a custom tag
Create a honeytoken
Create a honeytoken note
Create a honeytoken within a context
Create a team
Delete a custom tag
Delete a custom tags key
Retrieve a custom tag
Check API health status
Retrieve a honeytoken
Retrieve quota overview
Retrieve secret incident details
Retrieve current API token details
Ignore a secret incident
List API tokens
List all existing event names for audit logs
List audit logs for your workspace
List custom tags
List health check history for an instance
List health checks
List all honeytokens events
List honeytoken notes
List sources where a honeytoken appears
List honeytokens
List IP allowlist rules
List GitGuardian's own IP addresses
List workspace members
List groups via SCIM
List members via SCIM
List secret incidents
List all sources
List team members
List teams
Scan multiple contents for secrets
Reset a honeytoken
Resolve a secret incident
Revoke a honeytoken
Revoke current API token
Scan content and create incidents automatically
Scan content for secrets
Trigger a health check
Trigger scans on sources
Full update of a custom tag
Partial update of a custom tag
Update a custom tags key
Update a honeytoken
Update a secret incident
Why Cursor?
Cursor's Agent mode turns GitGuardian into an in-editor superpower. Ask Cursor to generate code using live data from GitGuardian and it fetches, processes, and writes. all in a single agentic loop. 49 tools appear alongside file editing and terminal access, creating a unified development environment grounded in real-time information.
- —
Agent mode turns Cursor into an autonomous coding assistant that can read files, run commands, and call MCP tools without switching context
- —
Cursor's Composer feature can generate entire files using real-time data fetched through MCP. no copy-pasting from external dashboards
- —
MCP tools appear alongside built-in tools like file reading and terminal access, creating a unified agentic environment
- —
VS Code extension compatibility means your existing workflow, keybindings, and extensions all work alongside MCP tools
GitGuardian in Cursor
GitGuardian and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect GitGuardian to Cursor through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for GitGuardian in Cursor
The GitGuardian MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 49 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Cursor only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
GitGuardian for Cursor
Every tool call from Cursor to the GitGuardian MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I resolve a secret incident directly through the AI?
Yes. You can use the resolve_secret_incident tool by providing the incident ID. You can also use assign_secret_incident to delegate the fix to a specific team member.
How do I create a decoy credential to catch attackers?
Use the create_honeytoken tool. You can specify the type and name of the honeytoken, and GitGuardian will generate a decoy that alerts you if it's ever used.
Is it possible to scan a text block for secrets before I commit it?
Absolutely. Use the scan_content tool. Provide the document content and a filename, and the AI will return any detected secrets or policy violations found by GitGuardian's engine.
What is Agent mode and why does it matter for MCP?
Agent mode is Cursor's autonomous execution mode where the AI can perform multi-step tasks: reading files, editing code, running terminal commands, and calling MCP tools. Without Agent mode, Cursor operates in a simpler ask-and-answer mode that doesn't support tool calling. Always ensure you're in Agent mode when working with MCP servers.
Where does Cursor store MCP configuration?
Cursor looks for MCP server configurations in a mcp.json file. You can configure servers at the project level (.cursor/mcp.json in your project root) or globally (~/.cursor/mcp.json). Project-level configs take precedence.
Can Cursor use MCP tools in inline edits?
No. MCP tools are only available in Agent mode through the chat panel. Inline completions and Tab suggestions do not trigger MCP tool calls. This is by design. tool calls require user visibility and approval.
How do I verify MCP tools are loaded?
Open Settings → Features → MCP and look for your server name. A green indicator means the server is connected. You can also check Agent mode's available tools by clicking the tools dropdown in the chat panel.
Tools not appearing in Cursor
Ensure you are in Agent mode (not Ask mode). MCP tools only work in Agent mode.
Server shows as disconnected
Check Settings → Features → MCP and verify the server status. Try clicking the refresh button.
Explore More MCP Servers
View all →
Unbounce
4 toolsAutomate marketing tasks via Unbounce — retrieve landing pages, fetch captured leads, audit performance stats, and manage test variants easily.
Privy
12 toolsManage users and wallets via Privy — create users, search profiles, and manage embedded wallets directly from any AI agent.
AbuseIPDB
4 toolsAudit IP addresses — check abuse scores and reports via AI.
Resend
10 toolsAutomate transactional and broadcast email delivery via Resend — send messages, manage domains, audiences, and contacts directly from any AI agent.