SmartBear Swagger MCP connector
The SmartBear Swagger connector lets Claude, ChatGPT, Cursor, Microsoft Copilot and the Elaichi Agent search your APIs and domains in Swagger Studio, create or update API definitions, and run standardization checks, with each person signed in as themselves.
- Connects over OAuth
- Free 14-day trial
- No credit card
Find every API in Swagger Studio that mentions payments
Working in SmartBear Swagger with Elaichi
-
Looked in SmartBear Swagger
How to connect SmartBear Swagger to Claude, ChatGPT, Cursor or Microsoft Copilot
Step by step, for each AI app
SmartBear Swagger MCP connector for Claude
-
1
Open Customize, then Connectors.
-
2
Press Add.
-
3
Name it, paste the MCP server URL, then Continue.
https://api.elaichi.ai/mcp -
4
Sign in and approve.
On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.
SmartBear Swagger MCP connector for Claude Code
-
1
In a terminal, run
claude mcp addwith the endpoint.https://api.elaichi.ai/mcp -
2
Start Claude Code and run
/mcp. -
3
Pick elaichi, then sign in and approve in the browser.
Terminal
$ claude mcp add --transport http elaichi --scope user https://api.elaichi.ai/mcp
Use --scope project instead to share it with the repository through .mcp.json.
SmartBear Swagger MCP connector for ChatGPT
-
1
Open Plugins, then press the + button.
-
2
Name it and paste the endpoint into Server URL.
https://api.elaichi.ai/mcp -
3
Leave Authentication on OAuth, then tick the risk acknowledgement.
-
4
Press Create, then sign in and approve.
Works on the web. The plugin directory lives at chatgpt.com/plugins.
SmartBear Swagger MCP connector for Cursor
-
1
Open
~/.cursor/mcp.json. -
2
Add the endpoint under
mcpServers.https://api.elaichi.ai/mcp -
3
Reload Cursor, then sign in and approve.
~/.cursor/mcp.json
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
Set up per machine, so repeat it on each computer you work from.
SmartBear Swagger MCP connector for Microsoft Copilot
-
1
In Copilot Studio, open your agent, then Tools, Add a tool, New tool and Model Context Protocol.
-
2
Paste the endpoint into Server URL, choose OAuth 2.0, then Dynamic discovery, and press Create.
https://api.elaichi.ai/mcp -
3
Create a new connection, sign in and approve, then press Add to agent.
-
4
Under Channels, open Teams and Microsoft Copilot and make the agent available in Microsoft Copilot.
- Server URL
- https://api.elaichi.ai/mcp
- Authentication
- OAuth 2.0
- Type
- Dynamic discovery
Microsoft Copilot was called Microsoft 365 Copilot. Keep the tool on end-user credentials, so each person signs in as themselves.
Connect SmartBear Swagger to any MCP client
-
1
Add the endpoint as a remote MCP server.
https://api.elaichi.ai/mcp -
2
Sign in and approve.
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
The Elaichi Agent already has these tools, with nothing to set up.
What teams do with SmartBear Swagger through Elaichi
Ask in plain English. Each person’s AI can do only what they’re allowed to, and every action it takes in SmartBear Swagger is logged.
-
Platform engineering
Find the API before building another
Ask whether an API for a given capability already exists in Swagger Studio and get the matching definitions back, so nobody drafts a duplicate.
-
API product
Draft a new API definition from a brief
Turn a short description of a service into a first API definition in SmartBear Swagger, ready for the team to review and refine.
-
Architecture
Check a definition against the house standards
Run standardization checks on an API definition and get a plain list of what fails and why, before it reaches a review meeting.
-
Developer experience
Keep shared domains current
Update a shared domain in Swagger Studio when a common model changes, so every API that reuses it picks up the fix.
-
QA
Catch standards failures before review
Ask for the open standardization failures on an API and work through them one by one, then rerun the check to confirm they are gone.
-
Partner engineering
Answer what an API actually exposes
When a partner asks what a public API offers, search Swagger Studio for the definition and summarize its endpoints and fields in an answer.
Try asking
- “Find every API in Swagger Studio that mentions payments”
- “Draft an API definition for the orders service from this brief”
- “Run standardization checks on the customer API and list what fails”
What connecting SmartBear Swagger gets you
5 screens from Elaichi, each doing one job for your SmartBear Swagger account.
Ask Elaichi to work across your apps.
Find every API in Swagger Studio that mentions payments
Draft an API definition for the orders service from this brief
Run standardization checks on the customer API and list what fails
Also runs in Claude, ChatGPT, Cursor or Microsoft Copilot
The agent
Ask about your APIs in plain language.
Search Swagger Studio, draft definitions and run standardization checks without opening a tab.
Copy the endpoint
AI apps
SmartBear Swagger works from every MCP client.
Claude, ChatGPT, Cursor and Microsoft Copilot share one governed endpoint, no SDK and no shared API key.
Toolboxes
Each team gets its own SmartBear Swagger toolbox.
Platform, architecture and QA each see the SmartBear Swagger tools their work needs.
Shared connections
Share one SmartBear Swagger connection, keep the credential.
Teammates search and update API definitions through your connection without ever seeing a credential.
Audit log
Every SmartBear Swagger call is on the record.
Who changed which API definition, when, and from which client, in one append-only log.
From answering questions to doing the work
A trigger starts the work, inside the same permissions and the same audit log as everything else. Workflows, collections and live dashboards come with the Black plan.
SmartBear Swagger digest
Run 418 · started 2 minutes ago · on behalf of Emily Carter
-
✓
Schedule
Every weekday at 8:00 AM
0.2s -
✓
Fetch apis
SmartBear Swagger
1.4s -
✓
Group by owner
Transform
0.1s -
✓
Draft the digest
Agent step
Ran with 4 tools, returned a structured summary
6.2s -
Approve the digest
Needs approval
Assigned to Jake Morgan
Approve Deny -
Post the digest
SmartBear Swagger
Queued
Workflows
Schedules run SmartBear Swagger checks end to end.
New API definitions are fetched, grouped and summarized, approved by a person, then posted back.
SmartBear Swagger health
Refreshed 4 minutes ago · every 15 minutes · from the apis collection
Apis
1,284 ↓ 12%
Domains
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Apis created
Last 14 days
By team
Share of activity
Platform 34%
Architecture 27%
API product 21%
QA 18%
Collections and dashboards
API health numbers arrive without anyone asking.
Definitions created, checks run and failures by team, refreshed on a schedule with no model involved.
Why connect SmartBear Swagger's MCP server through Elaichi
SmartBear Swagger builds and runs this MCP server. Elaichi sits in front of it, so SmartBear Swagger's tools follow the same sign-in, access rules and audit log as every other connector your organization uses. Calls an AI client makes to SmartBear Swagger's server directly, outside Elaichi, get none of this.
-
One address for every AI client
Claude, ChatGPT, Cursor and Microsoft Copilot reach SmartBear Swagger's tools at the same Elaichi address as every other connected app. Nobody adds SmartBear Swagger's server to each client one by one.
-
Each person signs in as themselves
Each person signs in to Elaichi as themselves. Members connect with their own SmartBear Swagger sign-in, and a connection someone shares runs on its owner's account. The credential stays in Elaichi's separate credential service, and the AI client holds only its Elaichi sign-in.
-
Rules checked before a call leaves
Restrictions on a role or a person, for the whole connector or a single tool, are checked before a call reaches SmartBear Swagger's server. By default, a tool SmartBear Swagger does not mark read-only or non-destructive counts as destructive, and over MCP it still runs under the "Use your connected apps" consent.
-
One audit log for every app
Each call that runs is recorded with the person, the tool, the connection and the AI client that made it, in the same audit log as every other app.
-
Tool issues go to SmartBear Swagger
SmartBear Swagger builds and runs these tools, and Elaichi staff do not curate them, so a report about how a tool behaves goes to the SmartBear Swagger team.
For IT and engineering
Elaichi vs Zapier MCP vs Composio for SmartBear Swagger
All three can connect SmartBear Swagger to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.
| What to check | Elaichi | Zapier MCP | Composio |
|---|---|---|---|
| Where the AI connects |
One address for the whole organization.
https://api.elaichi.ai/mcp
|
A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over SmartBear Swagger tools | Allow or restrict single SmartBear Swagger tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per SmartBear Swagger call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | Free for one person; $15 per user per month on Gold. | 2 tasks per successful call. | Billed per tool call. |
Sources: Zapier MCP docs, security, usage; Composio docs, gateway, enterprise, pricing. Checked September 2026.
Longer take: Zapier MCP alternative and when you don't need an MCP gateway.
Questions, answered
How do I connect SmartBear Swagger to Claude?
Open Elaichi, choose SmartBear Swagger, and sign in with your SmartBear account when the OAuth screen appears. There is no OAuth application to register and no client ID or secret to generate. Then in Claude go to Customize, then Connectors, then Add, and paste the endpoint https://api.elaichi.ai/mcp. Claude will ask you to sign in to Elaichi, and from then on it can work with your APIs in Swagger Studio.
Does SmartBear Swagger work with ChatGPT and Cursor as well as Claude?
Yes. The SmartBear Swagger connector is reached through the same endpoint, https://api.elaichi.ai/mcp, from Claude, ChatGPT, Cursor, Microsoft Copilot, any MCP client and the Elaichi Agent. You connect SmartBear Swagger once in Elaichi and every client you use picks it up.
What can an AI agent actually do with my SmartBear Swagger data?
An agent can search the APIs and domains in your Swagger Studio, create a new API definition or update an existing one, and run standardization checks and tell you what fails. Short, concrete asks work best, such as asking for the definition of one named API or a check on one definition rather than a long paragraph of instructions.
Does connecting SmartBear Swagger give the AI every API in my organization?
No. The agent works inside the access of the person who signed in to SmartBear Swagger, so it only sees the APIs and domains that person can already open in Swagger Studio. Elaichi can narrow that further with roles and restrictions, and it can never widen what SmartBear Swagger itself allows.
Can I stop an agent from changing API definitions in SmartBear Swagger?
Yes. Restrictions in Elaichi apply per action, so you can allow searching Swagger Studio and running standardization checks while restricting the creation or update of API definitions. A restricted action still appears in Elaichi's tool search, flagged as restricted, but Claude, ChatGPT, Cursor or Microsoft Copilot cannot run it, whatever the prompt says.
What happens to a SmartBear Swagger connection when someone leaves?
Offboarding that person in Elaichi ends their access to SmartBear Swagger through every client at once. A shared SmartBear Swagger connection keeps working for everyone else on the team. If you want the connector gone entirely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor, Microsoft Copilot and every other client.
Does the SmartBear Swagger MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. SmartBear Swagger is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, Microsoft Copilot, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.
Is Elaichi an alternative to Zapier MCP for SmartBear Swagger?
Yes. Both let Claude, ChatGPT or Cursor use SmartBear Swagger. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every SmartBear Swagger call.
How is Elaichi different from Composio for SmartBear Swagger?
Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to SmartBear Swagger: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.
Put SmartBear Swagger in front of your team
14 days of Black, no credit card. Connect it once and pick what each team can call.
When the trial ends, nothing is deleted. You move to the free Personal plan, and connections, roles and the audit log stay where they are.
Add one link to your AI app
The same link for everyone on your team.
https://api.elaichi.ai/mcp
ChatGPT
Claude
Cursor
Microsoft Copilot