
Connect Insomnia Collaborative API Design to your AI
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. Manage your entire API lifecycle without leaving your AI client.
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.

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.
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.
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.
01-04
4 capabilities in this set.
Part of 10 available through Insomnia.
- 01
List branches
This capability lists the Git-like branches for an Insomnia file. Use it to track progress across parallel feature branches.
- 02
List collaborators
This capability returns a list of members in an Insomnia organization. It provides usernames, emails, roles, and access levels.
- 03
List mocks
This capability retrieves the mock servers within an Insomnia project. It shows names, URLs, and current statuses.
- 04
Get file
This capability fetches the full details of an Insomnia file. You get the name, type, version history, and the JSON content for specs or collections.
05-07
3 capabilities in this set.
Part of 10 available through Insomnia.
- 05
Get user
This capability pulls your authenticated Insomnia user profile. It returns your username, email, plan, and organization memberships.
- 06
List AI requests
This capability exposes metadata and usage metrics for Insomnia AI interactions. It lists AI-generated specs and test suggestions.
- 07
List environments
This capability lists the environments in an Insomnia project. It shows environment names and the count of variables like base URLs or tokens.
08-10
3 capabilities in this set.
Part of 10 available through Insomnia.
- 08
List files
This capability finds files within an Insomnia project. It returns names, types, and last modified dates to help you locate specific file_ids.
- 09
List orgs
This capability lists all organizations on Insomnia Cloud. It provides names, IDs, and member counts to help you find the right workspace.
- 10
List projects
This capability lists the team projects inside an Insomnia organization. It returns project names and IDs.
Real work
What teams actually run
Rapid Spec Inspection
An engineer needs to check an endpoint definition quickly and asks the agent for the file content.
Environment Verification
A tester checks if the correct base URL is set in a specific project environment.
Mock Server Health Checks
A developer verifies if a mock server is active and retrieves its URL for a test run.
Team Access Audits
A manager lists organization members and their roles to check permissions.
Automate a task
Put Insomnia 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
Insomnia 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.
Claude
ChatGPT
Gemini
Perplexity
Grok
Microsoft Copilot
Cursor
VS Code
Windsurf
JetBrains
Cline
LangChain
Vercel AI SDK
Lovable
Z.ai
Raycast
Qwen Code
Kimi Code
Le ChatBuilding your own app? The connector is yours to use.
You don't need a client to put Insomnia 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
904ms average. Fast in production.
Insomnia is checked daily against the live service.
- Fastest day
- 821ms
- Slowest day
- 1047ms
- 14-day trend
- Slowing+24%
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 Insomnia, so you can see the experience inside your AI.
It does not authenticate your account with Insomnia. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.
Insomnia Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_llyGrXZujRu3thzxemiC8Hu0c2yGytKkiHgDZtDU/mcpClaude 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 — Insomnia capabilities are ready to use.
{
"mcpServers": {
"insomnia-collaborative-api-design-mcp": {
"url": "https://edge.vinkius.com/vk_preview_llyGrXZujRu3thzxemiC8Hu0c2yGytKkiHgDZtDU/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 Insomnia in Claude and other AIs
Who it's for
Built for the work Insomnia owners hand off.
This MCP is built for technical teams managing complex API lifecycles through Insomnia Cloud.
- 01
API Developers
They ask the agent to fetch OpenAPI specs and request collections without opening the desktop app.
- 02
QA Engineers
They use the agent to audit mock server statuses and environment variables for testing.
- 03
Software Architects
They monitor API design progress and feature branches across multiple team projects.
FAQ
Questions Insomnia owners ask.
- 01
How do I connect my Insomnia account?
You subscribe to the MCP on Vinkius and enter your Insomnia Personal Access Token. Once connected, your AI client can immediately access your Insomnia Cloud data.
- 02
Which AI clients can I use with this MCP?
You can use any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.
- 03
Can I see my OpenAPI specs through the AI?
Yes. You can use the get_file capability to retrieve the full JSON content of your OpenAPI or Swagger specifications.
- 04
Does this work with Insomnia Cloud?
Yes, this MCP is specifically designed to connect to your Insomnia Cloud account.
- 05
Can I manage team permissions?
You can use the list_collaborators capability to view usernames, emails, roles, and access levels for members in your organization.
- 06
Can I fetch full OpenAPI specifications through my agent?
Yes. Use the get_file capability by providing the relevant Org, Project, and File IDs. Your agent will retrieve the exact content payload, allowing you to inspect or summarize the API structure directly in your workspace.
- 07
How do I see the environments defined in a team project?
The list_environments capability allows your agent to extract base environments scoped within a project. You'll see the environment names and variable counts, helping you identify available stages for your API calls.
- 08
Can my agent check if a mock server is currently online?
Absolutely. Use the list_mocks capability to retrieve all mock servers linked to your projects. Your agent will report their current operational state, names, and hosted URLs for testing purposes.
Explore
More in Loved By Devs
Katalon TestOps (AI Test Management) AI Connector
Manage test orchestration via Katalon TestOps — rerun test runs, monitor execution results, and audit software
ViewTestRail AI Connector
Browse TestRail suites, parse manual test specs, and monitor active runs seamlessly native within your convers
ViewTestLink AI Connector
Navigate your self-hosted TestLink instance to inspect test plans, suites, cases, and builds natively via your
ViewPixso AI Connector
Collaborative design platform and UI/UX tool — manage design files, nodes, and teams via AI.
View
Suggestions
Testim AI Connector
Trigger automated AI tests, inspect execution logs, and manage branches natively via your AI agent.
ViewWine Label Design Testing AI Connector
Design valid A/B testing protocols for wine labels using statistical experimental design.
ViewIntra-Set Rest-Pause Planner AI Connector
Design high-intensity rest-pause protocols to maximize effective repetitions.
ViewZephyr Scale (SmartBear) AI Connector
Manage test cases, cycles, and executions on Zephyr Scale — the high-performance test management tool for Jira
View
Connect Insomnia to Claude, Cursor, ChatGPT & more
