How do I connect this MCP to my AI client?

You connect once through the Vinkius platform. Vinkius hosts the MCP and manages the connection, so you just need to authorize it in your preferred client like Claude or Cursor.

What credentials do I need to provide?

You will need to provide a valid SWAGGERHUB_KEY. This key allows the MCP to authenticate with your SwaggerHub organization securely.

Can my agent see all my APIs?

Yes, if your SWAGGERHUB_KEY has the appropriate permissions, your agent can list and retrieve any API, project, or domain within your organization.

Does this work with my CI/CD pipelines?

Yes. The MCP includes capabilities to list and verify integrations with services like AWS, GitHub, and GitLab, allowing your agent to check sync statuses.

Is this just a way to read documentation?

It goes beyond reading. It allows your agent to actively query the API lifecycle, check integration statuses, and pull raw JSON schemas for technical tasks.

Can the agent interact with public APIs outside my specific organizational ecosystem?

Yes. Beyond listing your own API configurations, the integration includes powerful global metadata capabilities like search_apis allowing you to query keyword structures discovering public interfaces readily.

How securely does the system parse potentially heavy or oversized API configurations locally?

Yes. The integration parses large JSON configurations securely and natively, ensuring large multi-megabyte API definitions are safely parsed without memory timeouts.

Can the AI modify or publish new API specifications?

The integration is primarily read-oriented. it retrieves specs, domains, projects, and integration configs. To publish or edit specs you would use the SwaggerHub editor or its write API endpoints separately.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect SwaggerHub 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. Pull OpenAPI specs and manage your API lifecycle without leaving your chat.

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.

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.

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 · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through SwaggerHub.

01
Get project details
Retrieves specific details for a SwaggerHub project.
02
List API templates
Shows all available API templates within SwaggerHub.
03
List projects
Lists every project inside a SwaggerHub organization.
04
Get domain details
Fetches metadata for a specific SwaggerHub domain.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through SwaggerHub.

05
Get API details
Returns metadata for a specific API definition.
06
Get API version spec
Pulls a specific version of an OpenAPI specification from SwaggerHub.
07
List API integrations
Lists the CI/CD integrations configured for a specific API.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through SwaggerHub.

08
List apis
Retrieves all API definitions owned by a user or organization.
09
List domains
Lists all shared, reusable component domains in an organization.
10
Search apis
Searches the SwaggerHub public registry for APIs using keywords.

Real work

What teams actually run

Automated Code Generation

Your agent pulls a specific OpenAPI spec to provide the exact schema needed for generating client libraries.

CI/CD Health Checks

You ask your agent to confirm if an API's AWS or GitHub integration is currently synced and active.

Component Reusability

The AI scans shared domains to ensure developers use existing definitions instead of creating new ones.

API Inventory Audits

You quickly list all projects and APIs within an organization to map out your technical landscape.

Automate a task

Put SwaggerHub 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

SwaggerHub 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.

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

You don't need a client to put SwaggerHub 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

917ms average. Fast in production.

SwaggerHub is checked daily against the live service.

Daily averagePeak 1092ms

Oct 3Today

Fastest day: 687ms
Slowest day: 1092ms
14-day trend: Stable+3%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 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 SwaggerHub, so you can see the experience inside your AI.

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

SwaggerHub Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_yxaBIFA3ShjsASSaz8QU0k25zGEdGatXEvFXcUe2/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — SwaggerHub capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "swaggerhub-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_yxaBIFA3ShjsASSaz8QU0k25zGEdGatXEvFXcUe2/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 SwaggerHub in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work SwaggerHub owners hand off.

This MCP is built for technical teams managing complex API ecosystems who want to interact with their documentation as data.

01
API Architects
They use the agent to pull JSON schemas for code generation and structural validation.
02
DevOps Engineers
They verify that CI/CD pipelines match the deployed API definitions.
03
Technical Writers
They pull correct, up-to-date definitions to draft documentation.

FAQ

Questions SwaggerHub owners ask.

01
How do I connect this MCP to my AI client?
You connect once through the Vinkius platform. Vinkius hosts the MCP and manages the connection, so you just need to authorize it in your preferred client like Claude or Cursor.
02
What credentials do I need to provide?
You will need to provide a valid SWAGGERHUB_KEY. This key allows the MCP to authenticate with your SwaggerHub organization securely.
03
Can my agent see all my APIs?
Yes, if your SWAGGERHUB_KEY has the appropriate permissions, your agent can list and retrieve any API, project, or domain within your organization.
04
Does this work with my CI/CD pipelines?
Yes. The MCP includes capabilities to list and verify integrations with services like AWS, GitHub, and GitLab, allowing your agent to check sync statuses.
05
Is this just a way to read documentation?
It goes beyond reading. It allows your agent to actively query the API lifecycle, check integration statuses, and pull raw JSON schemas for technical tasks.
06
Can the agent interact with public APIs outside my specific organizational ecosystem?
Yes. Beyond listing your own API configurations, the integration includes powerful global metadata capabilities like search_apis allowing you to query keyword structures discovering public interfaces readily.
07
How securely does the system parse potentially heavy or oversized API configurations locally?
Yes. The integration parses large JSON configurations securely and natively, ensuring large multi-megabyte API definitions are safely parsed without memory timeouts.
08
Can the AI modify or publish new API specifications?
The integration is primarily read-oriented. it retrieves specs, domains, projects, and integration configs. To publish or edit specs you would use the SwaggerHub editor or its write API endpoints separately.

Explore

More in Developer Tools

Connect SwaggerHub to Claude, Cursor, ChatGPT & more

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

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

Get project details

List API templates

List projects

Get domain details

05-07

Get API details

Get API version spec

List API integrations

08-10

List apis

List domains

Search apis

What teams actually run

Automated Code Generation

CI/CD Health Checks

Component Reusability

API Inventory Audits

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

SwaggerHub Connector

Claude Desktop

API Architects

DevOps Engineers

Technical Writers

How do I connect this MCP to my AI client?

What credentials do I need to provide?

Can my agent see all my APIs?

Does this work with my CI/CD pipelines?

Is this just a way to read documentation?

Can the agent interact with public APIs outside my specific organizational ecosystem?

How securely does the system parse potentially heavy or oversized API configurations locally?

Can the AI modify or publish new API specifications?

Pixso AI Connector

Insomnia (Collaborative API Design) AI Connector

Lanhu AI Connector

MasterGo AI Connector

Suggestions

Intra-Set Rest-Pause Planner AI Connector

Design Pickle AI Connector

Albi Restoration AI Connector

API Design Prover AI Connector