How to Use the MintMCP MCP in Claude Code

Q: How do I add MintMCP to Claude Code via the CLI?

Run the command claude mcp add --transport http mintmcp -- in your terminal. Ensure all transport flags are placed before the server name. You can verify the installation by running claude mcp list.

Q: How does MintMCP handle policy checks in Claude Code?

The agent uses mintmcpgettoolpolicy to fetch the active SOC2 governance rules before running commands. This ensures your automated scripts never violate access controls, even when running completely unattended in a pipeline.

Q: What tools are exposed to the CLI?

You can run mintmcplistavailabletools to see exactly which commands are approved for your current virtual server. This lets you audit the active toolset directly from your terminal output before starting a run.

Q: Where are my system audit logs stored?

All access logs and session details are retrieved via mintmcpfetchauditlogs. The MCP Server tracks access tokens and execution telemetries in a secure SOC2 matrix, ensuring a complete audit trail of every terminal action.

Secure your CI/CD pipelines and headless terminal runs with this enterprise MCP gateway for Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MintMCP MCP to Claude Code

Create your Vinkius account to connect MintMCP to Claude Code 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 MintMCP with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run terminal commands securely with this MCP Server

`mintmcp_run_tool_action` allows Claude Code to execute backend operations directly from your shell or CI pipeline. Since this client operates entirely in the terminal, it needs a reliable way to pipe commands to external APIs. The MintMCP gateway acts as the secure proxy for these runs. You don't have to manage local credentials on every runner or container running Claude Code. The agent routes its execution requests through MintMCP, which handles the auth and proxying behind the scenes. This keeps your deployment scripts clean and secure.

Run real-time parameter sanitization in scripts

`mintmcp_eval_guardrail` checks your command inputs and script parameters for potential exploits or raw secrets. Claude Code can easily leak environment variables or execute malformed shell arguments. This tool inspects the strings before they hit your infrastructure. The check runs inline with your pipeline execution. If the MintMCP guardrail engine detects a violation, it blocks the Claude Code action and returns a clean error. This prevents compromised inputs from reaching your internal networks.

Terminate remote runner sessions programmatically

`mintmcp_revoke_access_token` lets you kill a session from any shell script or cron job. If a build container running Claude Code finishes its run, you can programmatically destroy its access token. This ensures no stale sessions are left active on your network. It provides a clean way to manage ephemeral access. You don't have to wait for tokens to expire naturally. You control the exact lifecycle of the connection directly from your terminal commands.

Setup guide

Set up MintMCP MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see mintmcp-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest MintMCP transactions." It will automatically discover and invoke the available MintMCP tools.

Terminal

claude mcp add --transport http mintmcp-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the MintMCP MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "mintmcp-mcp": {
      "type": "url",
      "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 MintMCP. 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 MintMCP 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 MintMCP MCP in Claude Code

Run the command `claude mcp add --transport http mintmcp -- ` in your terminal. Ensure all transport flags are placed before the server name. You can verify the installation by running `claude mcp list`.

Yes, the gateway is designed for headless execution, allowing Claude Code to run automated tasks via command-line scripts. You can manage MCP access policies remotely without needing a graphical interface.

The agent uses `mintmcp_get_tool_policy` to fetch the active SOC2 governance rules before running commands. This ensures your automated scripts never violate access controls, even when running completely unattended in a pipeline.

You can run `mintmcp_list_available_tools` to see exactly which commands are approved for your current virtual server. This lets you audit the active toolset directly from your terminal output before starting a run.

All access logs and session details are retrieved via `mintmcp_fetch_audit_logs`. The MCP Server tracks access tokens and execution telemetries in a secure SOC2 matrix, ensuring a complete audit trail of every terminal action.

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