MintMCP Connector for AI agents.
8 live capabilities
Secure enterprise proxy routing for SOC2 compliant AI workflows.
Waiting for input…
Why people use MintMCP
MintMCP Enterprise Security for SOC2 Compliant AI Workflows
MintMCP changes that by putting a dedicated gateway in front of your capabilities. Instead of letting an agent wander freely, you route everything through virtual servers. This gives you a single point of control where you can enforce PII redaction and RBAC rules. You get the freedom to use your capabilities while the security team gets the logs they need to sleep at night.
What Vinkius changes
That it puts a secure, auditable wall between your AI agents and your sensitive company data.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Preventing PII leaks in customer support
A security team needs to ensure an agent doesn't leak customer emails.
- Real-world use case 02
Departmental capability provisioning
An admin needs to see what capabilities are available to a specific department.
- Real-world use case 03
Post-incident security auditing
A developer needs to audit a series of automated actions from last night.
Complete set · 8capabilities
The complete MintMCP capability set.
These are the exact actions your AI can choose when you ask it to work with MintMCP.
01—04
4 capabilities in this set.
Part of 8 available through MintMCP.
- 01 Capability
Mintmcp get capability policy
Fetches the specific RBAC and governance parameters for a capability. You can check exactly what rules are in place for a specific function.
- 02 Capability
Mintmcp get virtual server
Pulls the exact configuration for a single Virtual Server. Use it to inspect the schema of a specific proxy group.
- 03 Capability
Mintmcp list available capabilities
Shows which capabilities are currently approved inside a specific Virtual Server. This helps you see exactly what your agent can actually do right now.
- 04 Capability
Mintmcp list virtual servers
Lists all the proxy abstractions you've set up to group capabilities. Use this to see your entire organized topology at a glance.
05—08
4 capabilities in this set.
Part of 8 available through MintMCP.
- 05 Capability
Mintmcp revoke access token
Ends an active OAuth flow immediately. It's your panic button to isolate a compromised session.
- 06 Capability
Mintmcp run capability action
Proxies an execution stream to your native integrations. This is how the agent actually performs work through the gateway.
- 07 Capability
Mintmcp eval guardrail
Checks a string against your security and PII redaction engines. It ensures no sensitive data slips through the cracks.
- 08 Capability
Mintmcp fetch audit logs
Dumps the systematic telemetries for your SOC2 matrix. It provides a complete history of every access event.
Set up in minutes
One URL. Then ask MintMCP to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use MintMCP 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_O150J9v0kxg8rdyosRWdbRwIt3xDeHzZmIR4xy76/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 MintMCP, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable MintMCP for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_O150J9v0kxg8rdyosRWdbRwIt3xDeHzZmIR4xy76/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 MintMCP URL.
- Step 03
Save and start
Save the connection and enable MintMCP in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"mintmcp": {
"url": "https://edge.vinkius.com/vk_preview_O150J9v0kxg8rdyosRWdbRwIt3xDeHzZmIR4xy76/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 MintMCP
Open Agent mode in chat and ask: "Using MintMCP, help me...". 8 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"mintmcp": {
"url": "https://edge.vinkius.com/vk_preview_O150J9v0kxg8rdyosRWdbRwIt3xDeHzZmIR4xy76/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 MintMCP
Ask Copilot: "Using MintMCP, help me...". 8 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"mintmcp": {
"url": "https://edge.vinkius.com/vk_preview_O150J9v0kxg8rdyosRWdbRwIt3xDeHzZmIR4xy76/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 MintMCP
Open Cascade and ask: "Using MintMCP, help me...". 8 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"mintmcp": {
"url": "https://edge.vinkius.com/vk_preview_O150J9v0kxg8rdyosRWdbRwIt3xDeHzZmIR4xy76/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 MintMCP
Ask Cline: "Using MintMCP, help me...". 8 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add mintmcp --transport http "https://edge.vinkius.com/vk_preview_O150J9v0kxg8rdyosRWdbRwIt3xDeHzZmIR4xy76/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 MintMCP
Ask Claude: "Using MintMCP, show me...". 8 tools are ready
Where the request belongs
Work MintMCP can move forward.
This is for the security lead who is terrified of a data leak and the platform admin who needs to manage dozens of AI connections without losing their mind.
Security Engineering Lead
Auditing agent actions to ensure they meet SOC2 requirements on a daily basis.
Enterprise Platform Admin
Provisioning virtual servers to organize internal capability access for different departments.
Compliance Officer
Reviewing audit logs to prove that PII redaction is actually working for the organization.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsAlpic
AI MCP infrastructure: deploy, manage, and monitor MCP servers programmatically via agents.
Runlayer
AI enterprise control plane: manage MCP servers, skills, agents, and security policies via agents.
Smithery
AI MCP registry: discover, search, and connect MCP servers to your agents via Smithery.
NetBird
Automate Zero Trust networking via NetBird. manage accounts, users, and access controls directly from any AI agent.
CyberArk Privilege Cloud
Manage privileged access via CyberArk. audit secure safes, checkout vaulted account passwords, monitor users, and terminate sessions directly from any AI agent.
PAN-OS
Connect PAN-OS to any AI agent via MCP.
Bring your own AI
Change the model, client or framework. Keep Mint 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 MintMCP.
The practical details behind the request, access and result.
How does MintMCP help with SOC2 compliance?
It provides a centralized audit trail for every action your AI agent takes. By logging all requests and enforcing RBAC policies, it makes it much easier to prove to auditors that your AI workflows are secure and governed.
Can MintMCP block my AI agent from sharing sensitive data?
Yes, that's a core feature. It uses built-in guardrails to scan for PII and other sensitive information, redacting it before it ever leaves your secure environment.
What are virtual servers in MintMCP?
Think of them as organized folders for your capabilities. Instead of giving an agent access to everything, you group specific capabilities into virtual servers and only give the agent access to the ones it actually needs.
Can I quickly cut off an AI agent if it starts acting up?
Absolutely. You can instantly revoke access tokens to kill a session. This isolates any potential issues without having to shut down your entire system.
Is MintMCP suitable for large enterprise environments?
It's specifically designed for them. It's built to handle complex governance, multi-tenant identities, and the kind of rigid security requirements that large companies face when deploying AI.
Does MintMCP work with my existing internal capabilities?
Yes, it acts as a proxy gateway. It sits between your AI client and your existing internal systems, routing the logic safely while applying your security rules.
Can I test payload parameters through the security Guardrails offline?
Yes, mapping direct values through eval_guardrail runs simulated queries bypassing the actual downstream proxy directly into the evaluation loop.
Are explicit SOC2 Audit Logs available natively to query via this agent integration?
Yes! Utilize fetch_audit_logs limiting explicitly standard parameters to unpack all capability executions securely bounded inside your tenant matrix natively.
How do virtual servers separate functional capabilities proxy instances natively?
By polling list_available_tools against a specific server ID, you extract rigidly grouped schemas bounded solely to that environment parameter.
One connection away
Give your agent a direct line to Mint.
Connect Mint once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available