Security Vulnerability Scanner Connector for AI agents.
3 live capabilities
Protect your codebase from AI-generated injection vulnerabilities
Waiting for input…
Why people use Security Vulnerability Scanner
Stop AI-generated injection risks with Security Vulnerability Scanner
With this MCP, you stop guessing. Instead of manually hunting for bugs, your agent can trigger a deep structural scan that understands the logic of the code. You get a clear answer on whether the code is safe to run, turning a high-risk workflow into a secure, automated pipeline.
What Vinkius changes
You get a structural security audit that catches the dangerous logic errors AI agents often introduce.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 6,100+ Connectors
- Real-world use case 01
Validating AI-generated PRs
A developer uses an agent to write a new API endpoint and immediately runs a scan to ensure no injection flaws were introduced.
- Real-world use case 02
Automated Security Gatekeeping
A DevOps engineer sets a policy that prevents any code from being merged if the scan detects a critical vulnerability.
- Real-world use case 03
Legacy Code Auditing
A security researcher uses the scanner to quickly map out the risk profile of an existing repository.
Complete set · 3capabilities
The complete Security Vulnerability Scanner capability set.
These are the exact actions your AI can choose when you ask it to work with Security Vulnerability Scanner.
01—03
3 capabilities in this set.
Part of 3 available through Security Vulnerability Scanner.
- 01 Capability
Check pattern definition
G., SQL_INJECTION) is supported. Validates if a specific vulnerability pattern is currently supported by the engine's logic
- 02 Capability
Get vulnerability summary
Provides a high-level overview of the security posture of a specific codebase. It helps you understand the overall risk level at a glance.
- 03 Capability
Scan source code
Performs a deep AST-based security scan on a specific file or directory. It looks at the code structure to find deep logic flaws.
Set up in minutes
One URL. Then ask Security Vulnerability Scanner to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Security Vulnerability Scanner from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_VzqULA3f5yxIBgbrQrruv8bMna461DtX1kzt5Mei/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Security Vulnerability Scanner, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Security Vulnerability Scanner for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_VzqULA3f5yxIBgbrQrruv8bMna461DtX1kzt5Mei/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Security Vulnerability Scanner URL.
- Step 03
Save and start
Save the connection and enable Security Vulnerability Scanner in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"security-vulnerability-scanner": {
"url": "https://edge.vinkius.com/vk_preview_VzqULA3f5yxIBgbrQrruv8bMna461DtX1kzt5Mei/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Security Vulnerability Scanner
Open Agent mode in chat and ask: "Using Security Vulnerability Scanner, help me...". 3 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"security-vulnerability-scanner": {
"url": "https://edge.vinkius.com/vk_preview_VzqULA3f5yxIBgbrQrruv8bMna461DtX1kzt5Mei/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Security Vulnerability Scanner
Ask Copilot: "Using Security Vulnerability Scanner, help me...". 3 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"security-vulnerability-scanner": {
"url": "https://edge.vinkius.com/vk_preview_VzqULA3f5yxIBgbrQrruv8bMna461DtX1kzt5Mei/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Security Vulnerability Scanner
Open Cascade and ask: "Using Security Vulnerability Scanner, help me...". 3 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"security-vulnerability-scanner": {
"url": "https://edge.vinkius.com/vk_preview_VzqULA3f5yxIBgbrQrruv8bMna461DtX1kzt5Mei/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Security Vulnerability Scanner
Ask Cline: "Using Security Vulnerability Scanner, help me...". 3 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add security-vulnerability-scanner --transport http "https://edge.vinkius.com/vk_preview_VzqULA3f5yxIBgbrQrruv8bMna461DtX1kzt5Mei/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Security Vulnerability Scanner
Ask Claude: "Using Security Vulnerability Scanner, show me...". 3 tools are ready
Where the request belongs
Work Security Vulnerability Scanner can move forward.
This is for developers and security engineers who use AI-driven coding capabilities and need to ensure that generated code doesn't open doors for attackers.
DevSecOps Engineer
Automating the validation of agent-generated pull requests to ensure they meet security standards.
Software Architect
Setting strict security thresholds that all AI-assisted code must pass before merging.
Backend Developer
Quickly checking if a block of code written by an agent contains injection vulnerabilities.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsDoppler
Manage secrets and environment variables via Doppler. list projects, audit secrets, and track activity logs from any AI agent.
PiLAB
Manage infrastructure and security via PiLAB. control PiVirt virtual machines, inspect PiTrust certificates, and oversee 3SO OAuth clients directly from any AI agent.
JSON Schema Validator
Validate JSON documents and lint schemas for structural integrity.
OOPSpam
Block spam submissions on your forms and comments with an AI-powered filter that catches bots without annoying real users.
X Ads (Twitter)
Connect your X Ads account to any AI agent. audit campaigns, analyze line item performance, and pull engagement reports through natural conversation.
Box
Store, share, and collaborate on files securely with enterprise-grade cloud content management and governance controls.
Bring your own AI
Change the model, client or framework. Keep Security Vulnerability Scanner connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Security Vulnerability Scanner.
The practical details behind the request, access and result.
How does the Security Vulnerability Scanner MCP find bugs in AI code?
It uses AST-based analysis, which means it looks at the actual structure and logic of the code rather than just searching for specific words. This allows it to find complex injection flaws that simple scanners miss.
Can I use the Security Vulnerability Scanner MCP to enforce my own coding standards?
Yes. You can use it to check if the code generated by your agent meets specific security thresholds you've defined, ensuring every piece of code stays within your safety limits.
Will this MCP work with my existing AI coding capabilities?
Yes, as long as you are using an MCP-compatible client like Claude, Cursor, or Windsurf, you can connect this capability and start scanning immediately.
What kind of vulnerabilities does the Security Vulnerability Scanner MCP detect?
It is specifically designed to catch structural risks like SQL injection, command injection, and path traversal that are common in improperly handled code logic.
Is this MCP better than a standard linter?
Yes, for security. While a linter checks for style and basic errors, this MCP performs deep structural analysis to find actual security vulnerabilities that could be exploited by attackers.
How does the scanner detect vulnerabilities?
The scanner uses Abstract Syntax Tree (AST) pattern matching to analyze the actual structure of the code, ensuring it identifies real execution paths while ignoring comments and strings.
What kind of vulnerabilities can it find?
It detects SQL injection, command injection, path traversal, insecure deserialization, and hardcoded credentials.
Can I enforce security rules?
Yes, you can use validate_security_policy to check if the scan results meet your specific maximum allowed thresholds for critical or high-severity issues.
Can I scan an entire project?
Yes, by using the scan_source_code capability and providing the root directory path as the target path.
What kind of vulnerabilities are covered?
It covers SQL injection, command injection, path traversal, insecure deserialization, and hardcoded credentials.
One connection away
Give your agent a direct line to Security Vulnerability Scanner.
Connect Security Vulnerability Scanner once. Keep it beside 6,100+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available