How to Use the YepCode MCP in Claude Code

Q: How do I connect YepCode using Claude Code?

Run the command: claude mcp add --transport http yepcode-mcp -- . This establishes the connection for headless execution. You'll find the config in your /.claude.json.

Q: Can YepCode manage process executions with Claude Code?

Yes, use listexecutions to check logs or getprocessdetails for specific run data. This is perfect for monitoring automated job failures inside a GitHub Action.

Q: Does YepCode help me list processes using Claude Code?

Absolutely. Running listprocesses gives your script an immediate inventory of all available backend functions, which you can then reference in other tools like runprocess.

Q: Can I check team availability with YepCode using Claude Code?

Yep. The listteams tool lets your script confirm which organizational teams are accessible for the current deployment scope, adding a layer of validation to multi-environment pipelines.

Q: What type of data does this YepCode MCP Server touch regarding data privacy?

This server touches account secrets. Use listsecrets to view them, but remember that credentials should always be managed as environment variables, not committed code.

Automate CI/CD pipelines with YepCode 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 YepCode MCP to Claude Code

Create your Vinkius account to connect YepCode 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 YepCode with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute Backend Logic Headlessly

For CI/CD, you need reliability. The `run_process` tool executes serverless code snippets in the cloud, letting your scripts handle complex integrations without needing a GUI or browser. This makes it ideal for running automated builds or testing backend logic inside a Docker container.

Audit Process Availability

Need to know what processes are available in the pipeline? Run `list_processes` to get the full list of YepCode capabilities. Then, use `get_process_details` if you need specific input/output requirements for a job. This lets your shell script validate its dependencies before deployment.

Manage Deployment Secrets

Never hardcode tokens in a pipeline. Use `list_secrets` to programmatically list all available account secrets. This helps your DevOps routine verify that the necessary credentials are present. Knowing what secrets exist keeps your deployments secure and auditable.

Setup guide

Set up YepCode 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 yepcode-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http yepcode-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 YepCode 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": {
    "yepcode-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 YepCode. 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 YepCode 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 YepCode MCP in Claude Code

Run the command: `claude mcp add --transport http yepcode-mcp -- `. This establishes the connection for headless execution. You'll find the config in your ~/.claude.json.

Yes, use `list_executions` to check logs or `get_process_details` for specific run data. This is perfect for monitoring automated job failures inside a GitHub Action.

Absolutely. Running `list_processes` gives your script an immediate inventory of all available backend functions, which you can then reference in other tools like `run_process`.

Yep. The `list_teams` tool lets your script confirm which organizational teams are accessible for the current deployment scope, adding a layer of validation to multi-environment pipelines.

This server touches account secrets. Use `list_secrets` to view them, but remember that credentials should always be managed as environment variables, not committed code.

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