How to Use the Zeev MCP in Claude Code

Q: How do I start a process flow using Zeev and Claude Code?

You use the createrequest tool. Your shell script sends a command with initial data, which triggers the entire multi-step workflow in Zeev. The job returns an ID you can then poll for status.

Q: What processes are available to me using Zeev and Claude Code?

Run listprocesses to get a manifest of all defined BPMN workflows. This list shows every process definition your scripts can interact with, letting you build robust pipelines.

Q: How do I manage task status in Zeev using Claude Code?

Use gettask or getrequest. These tools let your script check the exact state of a process instance or a single human-actionable task. This is how you automate waiting for approvals.

Q: If my pipeline fails early, how do I check my user details with Zeev and Claude Code?

Use getme to pull your current user data. This confirms who initiated the failing job, which is critical for logging and debugging in a CI/CD environment.

Automate Zeev workflows in CI/CD pipelines using 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 Zeev MCP to Claude Code

Create your Vinkius account to connect Zeev 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 Zeev with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Kick off workflows via scripts.

The `create_request` tool lets you script the start of a complex process. Instead of relying on an interface, your shell script hits this endpoint with parameters and triggers a full Zeev workflow instance. This is ideal for CI/CD pipelines: when code passes testing, one simple job execution can kick off an entire multi-stage approval flow in Zeev.

Inventory all available processes.

Before running any automation, you need to know what's there. Use `list_processes` to fetch a manifest of every process definition available in the system. This list lets your scripts dynamically choose which workflow ID to use. Paired with `get_process`, you can pull down the full structure and ruleset for a specific Zeev process, ensuring your script adheres exactly to the expected logic.

Monitor task state in headless mode.

When running in a Docker container or GitHub Action, you can't watch pop-ups. Use `get_request` and `list_requests` to poll for the status of your process instances. Your script checks this endpoint until it gets 'Completed,' allowing the pipeline job to proceed only when the workflow is done. If something goes wrong, use `cancel_request` in a cleanup step to ensure resources are freed up immediately.

Setup guide

Set up Zeev 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 zeev-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http zeev-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 Zeev 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": {
    "zeev-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 Zeev. 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 Zeev 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 Zeev MCP in Claude Code

You use the `create_request` tool. Your shell script sends a command with initial data, which triggers the entire multi-step workflow in Zeev. The job returns an ID you can then poll for status.

Run `list_processes` to get a manifest of all defined BPMN workflows. This list shows every process definition your scripts can interact with, letting you build robust pipelines.

Use `get_task` or `get_request`. These tools let your script check the exact state of a process instance or a single human-actionable task. This is how you automate waiting for approvals.

It touches workflow state records, including process definitions, active request instances, and pending tasks within the core Zeev system.

Use `get_me` to pull your current user data. This confirms who initiated the failing job, which is critical for logging and debugging in a CI/CD environment.

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