SwaggerHub Connector for AI agents.
10 live capabilities
Query your OpenAPI specifications and manage API designs directly from your workspace.
Waiting for input…
Why people use SwaggerHub
SwaggerHub OpenAPI Spec Management for API Architects
This Connector puts your entire API catalog into the same context window as your code. You can ask your agent to pull the specific JSON for a v2.0.0 endpoint or check if the AWS sync is green. You get a unified workflow where the documentation isn't a separate destination; it's just part of the conversation.
What Vinkius changes
That your AI gets a direct line into your API documentation without you having to copy-paste a single file.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Checking for shared components
A developer wants to know if a 'UserAuth' domain already exists before creating a new one.
- Real-world use case 02
Verifying deployment sync
A DevOps lead needs to know if the Billing API is synced with AWS.
- Real-world use case 03
Generating boilerplate code
A backend engineer asks the agent to pull the v2.
Complete set · 10capabilities
The complete SwaggerHub capability set.
These are the exact actions your AI can choose when you ask it to work with SwaggerHub.
01—04
4 capabilities in this set.
Part of 10 available through SwaggerHub.
- 01 Capability
Get api details
Pulls the basic information and metadata for a specific SwaggerHub API. Use this to see the high-level details of an existing definition.
- 02 Capability
Get project details
Provides the details and structure of a specific project in your workspace. It helps you see how different APIs are grouped together.
- 03 Capability
List apis
Lists all the API definitions owned by your user or organization. Use this to get a broad overview of your available specs.
- 04 Capability
List domains
Shows all the shared domains and reusable components in your account. This helps you avoid duplicating common API structures.
05—07
3 capabilities in this set.
Part of 10 available through SwaggerHub.
- 05 Capability
List api integrations
Lists the CI/CD integrations like AWS or GitHub for a specific API. Use this to verify that your deployment pipelines are correctly linked.
- 06 Capability
List projects
Shows all the projects within your SwaggerHub organization. This helps you navigate the overall structure of your team's work.
- 07 Capability
List api templates
Shows the list of available API templates on the platform. Use this to see standard starting points for new designs.
08—10
3 capabilities in this set.
Part of 10 available through SwaggerHub.
- 08 Capability
Search apis
Searches the public SwaggerHub registry for APIs based on your keywords. This is useful for finding external specifications.
- 09 Capability
Get api version spec
Fetches a specific version of an OpenAPI spec in JSON format. This is the primary way to get the raw data for your agent to read.
- 10 Capability
Get domain details
Shows the metadata for a shared domain or reusable component. Use this to understand how common pieces of your API are structured.
Set up in minutes
One URL. Then ask SwaggerHub to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use SwaggerHub from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_yxaBIFA3ShjsASSaz8QU0k25zGEdGatXEvFXcUe2/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it SwaggerHub, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable SwaggerHub for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_yxaBIFA3ShjsASSaz8QU0k25zGEdGatXEvFXcUe2/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the SwaggerHub URL.
- Step 03
Save and start
Save the connection and enable SwaggerHub in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"swaggerhub": {
"url": "https://edge.vinkius.com/vk_preview_yxaBIFA3ShjsASSaz8QU0k25zGEdGatXEvFXcUe2/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using SwaggerHub
Open Agent mode in chat and ask: "Using SwaggerHub, help me...". 10 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"swaggerhub": {
"url": "https://edge.vinkius.com/vk_preview_yxaBIFA3ShjsASSaz8QU0k25zGEdGatXEvFXcUe2/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using SwaggerHub
Ask Copilot: "Using SwaggerHub, help me...". 10 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"swaggerhub": {
"url": "https://edge.vinkius.com/vk_preview_yxaBIFA3ShjsASSaz8QU0k25zGEdGatXEvFXcUe2/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using SwaggerHub
Open Cascade and ask: "Using SwaggerHub, help me...". 10 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"swaggerhub": {
"url": "https://edge.vinkius.com/vk_preview_yxaBIFA3ShjsASSaz8QU0k25zGEdGatXEvFXcUe2/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using SwaggerHub
Ask Cline: "Using SwaggerHub, help me...". 10 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add swaggerhub --transport http "https://edge.vinkius.com/vk_preview_yxaBIFA3ShjsASSaz8QU0k25zGEdGatXEvFXcUe2/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using SwaggerHub
Ask Claude: "Using SwaggerHub, show me...". 10 tools are ready
Where the request belongs
Work SwaggerHub can move forward.
For the backend engineer who's tired of asking 'where is the spec for this?' and the DevOps lead who needs to verify integration statuses without manual audits.
API Architect
Validates that new designs follow existing shared domains and organizational standards during the design phase.
Backend Engineer
Pulls specific OpenAPI JSON schemas to ensure their code matches the latest production definitions.
DevOps Engineer
Checks the status of CI/CD syncs for AWS or GitHub to troubleshoot pipeline failures quickly.
Technical Writer
Pulls accurate endpoint lists to keep documentation current without manual data entry.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsApiary
Manage your API design-first workflows via Apiary. read blueprints, publish docs, and run tests directly from your AI agent.
Archbee
Manage documentation spaces, sync OpenAPI specs, and organize technical knowledge directly from your AI agent.
DocBreach
Real-time documentation discovery for AI agents. Discover, read, and extract any API documentation without browser rendering or API keys.
Postman
Design, test, and document APIs collaboratively with the world most popular API development platform used by millions of developers.
Insomnia (Collaborative API Design)
Manage API designs and collections via Insomnia. list organizations, projects, and files, and audit API specs.
Stoplight
Connect your AI to Stoplight. Design, document, and manage your API lifecycle, exploring workspaces and schemas effortlessly.
Bring your own AI
Change the model, client or framework. Keep SwaggerHub connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about SwaggerHub.
The practical details behind the request, access and result.
Can the SwaggerHub MCP help me generate code?
Yes, by pulling the exact OpenAPI JSON specs for your APIs, your agent can use that data to generate accurate client libraries, server stubs, or mock data.
How does the SwaggerHub MCP handle my API keys?
The Connector uses your SWAGGERHUB_KEY, which you provide in your client's credential setup. This ensures your agent can securely access your private workspace data.
Can I use the SwaggerHub MCP to see my team's projects?
Yes, the Connector can list all projects in your organization, giving your agent a high-level view of how different APIs are grouped and managed.
Does the SwaggerHub MCP work with AWS integrations?
Yes, it can specifically check the sync status of your AWS API Gateway integrations to ensure your documentation matches your deployed infrastructure.
How do I use the SwaggerHub MCP to find shared components?
You can simply ask your agent to list your shared domains. It will then show you all the reusable components available in your workspace.
Can the SwaggerHub MCP search for public APIs?
Yes, the Connector includes a capability to search the public SwaggerHub registry, allowing your agent to find and retrieve external API specifications for you.
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.
One connection away
Give your agent a direct line to SwaggerHub.
Connect SwaggerHub once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available