An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Vinkius MCP Catalog to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Give your agent a map to every available capability.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 12 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 12 available through Vinkius.

  1. 01

    Get connect token

    This capability returns a connection URL that includes a secret token. Use it to get the ready-to-use link for a specific MCP.

  2. 02

    Credentials status

    This capability checks if an MCP is fully configured. It tells you if credentials are missing or if OAuth is required.

  3. 03

    Get credentials schema

    This capability retrieves the specific credential fields an MCP requires. Use these keys to provide the necessary secrets via set_credentials.

  4. 04

    Get listing faqs

    This capability pulls the FAQ section for a specific MCP. It provides a list of questions and answers directly from the catalog.

Capability set02 / 03

05-08

4 capabilities in this set.

Part of 12 available through Vinkius.

  1. 05

    Get listing prompts

    This capability fetches example prompts and responses for an MCP. It helps your agent understand the expected interaction flow.

  2. 06

    Get listing

    This capability provides deep technical details for a single MCP. It returns the description, FAQs, prompt examples, and related MCPs.

  3. 07

    Get random listings

    This capability returns up to 10 random MCPs from the catalog. It's a quick way to sample available capabilities without a specific search query.

  4. 08

    Invoke tool

    This capability runs a specific operation on an MCP you already have connected. It executes the capability directly through Vinkius.

Capability set03 / 03

09-12

4 capabilities in this set.

Part of 12 available through Vinkius.

  1. 09

    Active mcps

    This capability lists all the MCPs you currently own or have installed in your account.

  2. 10

    List tools

    This capability pulls the full list of capabilities available within a specific MCP. It includes the name, description, and the exact input schema for every capability.

  3. 11

    Search catalog

    This capability searches the entire Vinkius catalog using natural language. It returns matching MCPs along with their capabilities and descriptions.

  4. 12

    Set credentials

    This capability saves the required credentials for an MCP. You must provide real values from your own vault to make the capabilities functional.

Real work

What teams actually run

01

Autonomous Capability Discovery

An agent identifies a need for a specific service and searches the catalog to find a matching MCP.

02

Automated Workflow Debugging

An agent checks the credentials_status to see why a capability call is failing.

03

Capability Auditing

A developer queries the catalog to see how many capabilities are available in a specific category like Social Media.

04

Onboarding New Integrations

An agent reads prompt examples to learn the correct way to use a newly discovered MCP.

Automate a task

Put Vinkius to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Vinkius works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Vinkius to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

488ms average. Fast in production.

Vinkius is checked daily against the live service.

Daily averagePeak 525ms
Oct 5Today
Fastest day
438ms
Slowest day
525ms
14-day trend
Stable+4%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 12 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Vinkius, so you can see the experience inside your AI.

It does not authenticate your account with Vinkius. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Vinkius Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_mgLuRhIN64QtERLUltG0fhiWwQraI7y7TZ9s8l3O/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Vinkius capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "vinkius-mcp-catalog-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_mgLuRhIN64QtERLUltG0fhiWwQraI7y7TZ9s8l3O/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Vinkius in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Vinkius owners hand off.

This is for people building autonomous systems that need to discover and use external capabilities without manual intervention.

  • 01

    AI Agent Developers

    They use this to programmatically find and test MCPs before adding them to a workflow.

  • 02

    Platform Architects

    They use the catalog to audit the available capability ecosystem and find gaps in capability.

  • 03

    Growth Engineers

    They monitor category trends and new MCP additions to plan strategic integrations.

FAQ

Questions Vinkius owners ask.

  • 01

    Do I need to provide my own API keys to use the catalog?

    No. The catalog itself is public and does not require credentials. You only need to provide credentials when you want to use a specific MCP's capabilities.

  • 02

    How does the agent know how to use a capability?

    The agent uses list_tools to get the exact input schema and get_listing_prompts to see real-world examples of how the capability is used.

  • 03

    Can I use this with any AI client?

    Yes, this works with any MCP-compatible client like Claude, Cursor, or Windsurf.

  • 04

    What is the debugger grade?

    The debugger grade is a metric provided by Vinkius to indicate the technical quality and reliability of an MCP.

  • 05

    How do I find capabilities for a specific task?

    Use the search_catalog capability with a natural language query describing what you want to achieve.

  • 06

    Do I need credentials to use this MCP?

    No. The Vinkius catalog is fully public. All search, browse, and detail operations work without any credentials.

  • 07

    What data does the search return?

    Search returns MCP cards with title, description, slug, capability count, debugger quality grade, and auth requirement. Results are ranked by relevance using AI-powered keyword extraction.

  • 08

    Can I filter by category and server type simultaneously?

    Yes. All filter parameters (category, tag, server_type) can be combined in both search and browse operations for precise results.

  • 09

    What does the debugger grade mean?

    Each MCP is scanned by the Vinkius Debugger, which grades quality from A (excellent) to F (critical issues). The grade reflects capability schema compliance, error handling, response consistency, and documentation completeness.

Explore

More in Growth Engine

Suggestions

Connect Vinkius to Claude, Cursor, ChatGPT & more