Zuplo MCP for AI. Manage APIs and Deployments in Chat.

Q: What is the difference between listdeployments and listenvironments?

listenvironments shows the available lifecycle stages (like 'working' or 'production') for a project. In contrast, listdeployments tracks the historical record of when configuration changes were actually pushed out to the gateway.

Q: How does Zuplo manage custom domains? Do I need listcustomdomains?

You run listcustomdomains directly through the agent. It retrieves and lists all configured DNS names for your API projects, saving you from manually checking domain records in multiple zones.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Connect to your AI in seconds.

Zuplo manages your API infrastructure—gateways, edge deployments, and consumer access—all via chat. Stop clicking through cloud consoles; let your agent provision identities, audit configs, or pull real-time traffic metrics for any project in seconds.

What your AI can do

List consumers

Retrieves a complete list of all active API key consumers in your account.

Create consumer

Creates a new identity for an external user to access your APIs.

Create deployment

Initiates and pushes a new version of your API configuration live across the edge network.

+ 7 more capabilities included

Audit Project Structure

List all existing projects and environments to map out your entire API integration setup.

Control Consumer Access

Create new API key consumers or revoke old ones instantly, controlling who accesses which gateway authentication.

Manage Deployments

Trigger configuration deployments to the global edge network or audit previous deployment history.

Verify Domain Names

Retrieve and manage custom DNS domains configured for every API project.

Analyze Traffic Performance

Monitor real-time gateway traffic, latency, and throughput metrics from the edge network.

Review Gateway Logic

Browse and list the exact configuration files that define your API gateway's routing rules and policies.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

Zuplo: 10 Tools for API Management

These tools allow your agent to interact with every core function of the Zuplo platform, from listing projects to managing consumer identities.

Make your AI actually useful.

Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.

Start using Zuplo on Vinkius

List Consumers

Retrieves a complete list of all active API key consumers in your account.

Create Consumer

Creates a new identity for an external user to access your APIs.

Create Deployment

Initiates and pushes a new version of your API configuration live across the edge...

Delete Consumer

Permanently removes an external user's access key from the system.

List Custom Domains

Lists every custom domain name assigned to your various API projects.

List Environments

Shows which operational environments (like 'staging' or 'testing') are available for a project.

List Files

Retrieves the configuration files that define how your gateway routes traffic and applies policies.

List Deployments

Gets a history of all previous deployment actions taken on the gateway.

Get Metrics

Pulls real-time data on gateway traffic, latency, and overall performance.

List Projects

Lists all API projects configured under your Zuplo account.

Security and governance baked right in.

Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.

Claude AI

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

Start a conversation

Open a new chat. The Zuplo integration is available immediately — no restart needed.

Antigravity

Configure Agent Environment

Open your Antigravity agent's workspace configuration or mcp-servers.json file.

Bind the Endpoint

Add the Vinkius endpoint URL to your agent's MCP connections list:

"mcp_servers": {
  "zuplo": {
    "serverUrl": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
  }
}

Provide your secure token in place of [YOUR_TOKEN_HERE] to ensure your agent requests are authenticated.

Execute

Start your Antigravity session. The agent will autonomously discover and utilize the Zuplo tools with full Vinkius guardrails applied.

VS Code Copilot

⚡

One-Click Install (Recommended)

In your Vinkius Dashboard, simply click the Add to VS Code button for this server. We'll automatically configure your local workspace.

Or configure manually

Open MCP Settings

Open VS Code, press Ctrl/Cmd + Shift + P, and search for GitHub Copilot: MCP Servers.

Add Server Config

Add the Vinkius endpoint configuration to your mcp-servers.json file:

"zuplo": {
  "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
}

Ensure you replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

LangChain

Install Dependencies

Install the LangChain MCP adapters for your environment:

pip install langchain-mcp-adapters

Connect the Server

Use the SSEClient in LangChain to connect to the Vinkius managed endpoint:

from langchain_mcp_adapters.client import SSEClient

# Connect to Vinkius
client = SSEClient(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
tools = client.get_tools()

CrewAI

Define the Tool

Load the Vinkius MCP tools into your CrewAI agents:

from crewai import Agent
from mcp_crewai import MCPTool

# Connect securely to Vinkius
vinkius_tools = MCPTool(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

# Assign to Agent
researcher = Agent(
    role='Data Researcher',
    tools=vinkius_tools.get_all()
)

Execute Task

Run your CrewAI process. The agent will autonomously route tasks to the Vinkius managed server.

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

Import from OpenAPI, Swagger, or YAML specs
Create Agent Skills with progressive disclosure
Deploy to edge with MCPFusion framework
Built in DLP, auth, and compliance on every call
Real time usage dashboard and cost metering
Publish to catalog or keep private

Start building

Make Your AI Do More

Start with Zuplo, then connect any of our 5,000+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 5,000+ others, all in one place
Add new capabilities to your AI anytime you want
Every connection is secured and compliant automatically
Track usage and costs across all your servers
Works with Claude, ChatGPT, Cursor, and more
New servers added to the catalog every week

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Zuplo. 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.

VINKIUS INFRASTRUCTURE

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on every call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

Your data is protected. See how we built it.

Works with Claude, ChatGPT, Cursor, and more

The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.

This connection provides 10 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

The constant dashboard clicking is exhausting.

Right now, if you need to see how many users are hitting a specific gateway and whether they have active permissions, you're stuck. You jump into the project console, find the metrics tab, switch views to check consumer lists, then navigate to the deployment history. It’s clicking through three different tabs just to answer one question.

With this MCP, you ask your agent: 'What are the current edge metrics for Project X, and who is consuming it?' The agent runs the necessary checks—pulling metrics, listing consumers, and verifying status—and hands you a single, consolidated report. It's immediate context.

Getting consumer access control with `list_consumers`.

Before adding an API key for a new partner, the typical process is to manually locate all existing consumers in the Zuplo UI. This involves searching through massive lists and confirming the correct project scope every time. It's tedious, slow, and error-prone.

Now, you simply ask your agent to `list_consumers`. The agent runs the tool and gives you a clean list of current users right in the chat window. You know exactly who has access without spending 15 minutes clicking through menus.

Support 24/7 support@vinkius.com ↗

Security Vinkius Trust Center ↗

SLA Service Level Agreement ↗

Report Listing Send Report ↗

What your AI can actually do with this

Managing an API gateway used to mean navigating a nightmare of nested menus: create the project, then list environments, then verify the custom DNS domains, and finally, if everything looked okay, manually generate a key. Now, you just talk to your AI agent. You tell it which projects need monitoring or who needs access, and it handles the whole lifecycle.

Need to check traffic latency? Just ask for metrics; no dashboard hopping required. When you connect this MCP through Vinkius, credentials pass through a zero-trust proxy—meaning your API keys are only used in transit, never stored on disk. This makes managing sensitive gateway authentication policies fast and secure. Your agent becomes the full platform engineer for Zuplo.

Built · Hosted · Managed by Vinkius Zuplo MCP - Manage APIs & Deployments

Server ID 019d762c-038b-70dd-b730-530ff4ff7cf9

Vinkius Inspector

Compliance Grade A+

Score 100/100

Report View Report ↗

What Changes When You Connect

Stop manually checking deployments. You can trigger new configurations using create_deployment with a simple command, immediately updating the global edge network.

Need to control access? Use list_consumers first, then run create_consumer or delete_consumer without ever touching a permissions panel.

Performance monitoring is instant. Just ask for metrics and get real-time data on latency and throughput using get_metrics, eliminating dashboard logging in your mind.

Debugging gateway logic gets easy. Instead of searching through logs, you can use list_files to see the exact configuration files defining routing policies.

Get a full picture of your setup by running list_projects and then following up with list_environments, giving you instant visibility into every corner of your API surface.

See it in action

01 01

Revoking Partner Access

A third-party vendor loses contract status. Instead of logging into the console and manually finding their credentials, the agent runs list_consumers to confirm their ID, then uses delete_consumer to instantly revoke all access.

02 02

Auditing Gateway Changes

A security review requires knowing who changed what. The engineer first calls list_projects, then runs list_deployments to see the full history of changes, ensuring no unauthorized deployments occurred.

03 03

Verifying Staging Readiness

Before a major release, the team needs proof that all environments are ready. The agent uses list_environments and checks the status across multiple projects to ensure nothing is stuck in an unknown state.

04 04

Mapping API Domains

A new region requires custom endpoints. The platform team runs list_custom_domains to see what's already configured, and then uses list_projects to scope the necessary additions.

The honest tradeoffs

Manual Console Navigation

Anti-pattern

Spending 45 minutes clicking through Zuplo's web UI—going from the project list, into environments, then finally finding the consumer management tab to delete a key.

The Fix

Tell your agent to list_projects and then delete_consumer. It handles the navigation flow and executes the action in two lines of chat.

Ignoring Environment Context

Anti-pattern

Assuming a change applied in 'development' automatically hits 'production.' Manual checks are always prone to error.

The Fix

Always run list_environments first. Then, when you need a deployment, use the targeted action and verify it with get_metrics on the specific environment.

Over-relying on GUI Lists

Anti-pattern

Getting lists of domains or configs just to copy them out into a spreadsheet for manual review.

The Fix

Use the agent to run list_custom_domains and then pass the output directly to another tool, like an automation script, without any manual copy/paste.

When It Fits, When It Doesn't

Use this MCP if your process involves coordinating actions across different stages of API lifecycle management. You need to monitor performance (get_metrics), manage access credentials (create_consumer, delete_consumer), and control the deployment state (using list_deployments or create_deployment). Don't use it if you only need to view simple data; for example, if you just want a list of projects, running list_projects is enough. If your goal requires complex automation—like changing an API key and updating billing records in another system—you should look into chaining this Zuplo MCP with other services within the Vinkius platform to build end-to-end workflows.

Questions you might have

How do I check gateway performance using `get_metrics`? +

Simply ask your agent to get edge metrics for the relevant project. The system returns real-time data on latency, traffic volume, and error rates without you needing to navigate a dedicated analytics dashboard.

What is the difference between `list_deployments` and `list_environments`? +

list_environments shows the available lifecycle stages (like 'working' or 'production') for a project. In contrast, list_deployments tracks the historical record of when configuration changes were actually pushed out to the gateway.

Can I create and delete users using `create_consumer` and `delete_consumer`? +

Yes, those tools handle the full consumer lifecycle. You tell your agent who needs access, it runs create_consumer, and when they leave, you use delete_consumer to revoke their key immediately.

How does Zuplo manage custom domains? Do I need `list_custom_domains`? +

You run list_custom_domains directly through the agent. It retrieves and lists all configured DNS names for your API projects, saving you from manually checking domain records in multiple zones.

I need to check the routing rules; how do I use `list_files`? +

It lists the specific configuration files that define your gateway’s routing and policy logic. This lets you audit what traffic patterns are currently allowed or restricted by your API project.

When starting with a new set of APIs, how does `list_projects` help me scope my work? +

It provides a complete inventory of all Zuplo projects connected to your account. This ensures you can quickly identify the exact project ID before attempting any deployments or consumer management.

If I need to update an API version, is `create_deployment` the right tool? +

Yes, triggering a deployment via this tool pushes new configurations to your edge network. You use it to initiate changes, which is necessary for rolling out updates or fixing bad versions.

How can I audit all active API key consumers without listing every project? Use `list_consumers`. +

Running this tool gives you a direct list of every provisioned consumer identity. This is the fastest way to check who has access and verify credentials for compliance checks.

Can I check my API gateway metrics through the agent? +

Yes. The get_metrics tool allows your AI agent to retrieve real-time traffic and latency data for any specific project ID, helping you monitor gateway performance directly through chat.

How do I create a new consumer identity for API key authentication? +

You can use the create_consumer tool. Provide the project ID and a JSON payload with the consumer's details, and Zuplo will provision the new identity for your API gateway instantly.

Is it possible to see my project's configuration files via conversation? +

Absolutely. Use the list_project_files tool to retrieve the declarative configuration files for your API project, allowing you to audit routing and policy definitions through your agent.

Connect to your AI in seconds.

List consumers

Create consumer

Create deployment

Zuplo: 10 Tools for API Management

Make your AI actually useful.

List Consumers

Create Consumer

Create Deployment

Delete Consumer

List Custom Domains

List Environments

List Files

List Deployments

Get Metrics

List Projects

Security and governance baked right in.

Claude AI

Open Claude Settings

Add Custom Connector

Start a conversation

Claude Code

Open your terminal

Add the MCP Server

Start coding

Cursor

One-Click Install (Recommended)

Open Cursor Settings

Add New Server

Use in Composer

Antigravity

Configure Agent Environment

Bind the Endpoint

Execute

VS Code Copilot

One-Click Install (Recommended)

Open MCP Settings

Add Server Config

Windsurf

One-Click Install (Recommended)

Open Windsurf Settings

Add Server Endpoint

LangChain

Install Dependencies

Connect the Server

CrewAI

Define the Tool

Execute Task

Choose How to Get Started

Build Your Own

Make Your AI Do More

Works with Claude, ChatGPT, Cursor, and more

The constant dashboard clicking is exhausting.

Getting consumer access control with `list_consumers`.

What your AI can actually do with this

Here's how it actually works

Who is this actually for?

What Changes When You Connect

See it in action

Revoking Partner Access

Auditing Gateway Changes

Verifying Staging Readiness

Mapping API Domains

The honest tradeoffs

Manual Console Navigation

Ignoring Environment Context

Over-relying on GUI Lists

When It Fits, When It Doesn't

Questions you might have