Swaggerhub for AI agents
SwaggerHub is a collaborative platform for designing, documenting, and versioning APIs built on the OpenAPI standard, used by teams to manage API definitions. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Swaggerhub.
Get an API's current definition
Retrieve the current OpenAPI definition for an API as a read-only check before proposing changes.
List versions of an API
Pull the list of published versions for an API so a team can confirm which one is live.
Add access control for a team
Grant a team access to an API only after the user confirms who should have permission.
44 Swaggerhub actions, graded by risk.
Every Swaggerhub action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
35Look things up. Allowed by default.
- swaggerhub.get_portalGet Portal
- swaggerhub.get_portalsGet Portals
- swaggerhub.search_apisSearch APIs
- swaggerhub.get_templatesGet Templates
- swaggerhub.get_definitionGet API Definition
- swaggerhub.get_owner_apisGet Owner APIs
- swaggerhub.get_user_rolesGet User Roles
- swaggerhub.search_domainsSearch Domains
- swaggerhub.get_api_versionsGet API Versions
- swaggerhub.list_attachmentsList Attachments
- swaggerhub.get_organizationsGet User Organizations
- swaggerhub.get_owner_domainsGet owner domains
- swaggerhub.get_portal_productGet Portal Product
- swaggerhub.get_resource_typesList Resource Types and Roles
- swaggerhub.get_domain_versionsGet Domain Versions
- swaggerhub.get_org_projects_v2Get Organization Projects V2
write
5Create and change things. Allow, or ask the user first.
- swaggerhub.update_portalUpdate Portal
- swaggerhub.add_access_control_for_teamsAdd Access Control for Teams
- swaggerhub.add_access_control_for_usersAdd Access Control for Users
- swaggerhub.update_access_control_for_teamsUpdate Access Control for Teams
- swaggerhub.update_access_control_for_usersUpdate Access Control for Users
destructive
4Delete, cancel or archive. Ask first, or deny outright.
- swaggerhub.remove_membersRemove Organization Members
- swaggerhub.delete_table_of_contents_entryDelete Table of Contents Entry
- swaggerhub.remove_access_control_for_teamsRemove Access Control for Teams
- swaggerhub.remove_access_control_for_usersRemove Access Control For Users
Swaggerhub in three steps.
- 01Your users connect SwaggerhubThey add their Swaggerhub api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “update Portal” can wait for the user, and “delete Table of Contents Entry” can be denied outright.
- 03Any agent can actYour agent calls Swaggerhub through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('swaggerhub', { read: 'allow', write: 'ask', // update_portal destructive: 'deny', // delete_table_of_contents_entry }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Swaggerhub connects.
Users add their Swaggerhub api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Swaggerhub connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Swaggerhub from any agent.
Swaggerhub and Arc0, answered.
Can I use Swaggerhub with Claude, ChatGPT or Cursor?
Yes. Connect Swaggerhub to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Swaggerhub actions you allow.
How do users connect Swaggerhub?
Users add their Swaggerhub api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Swaggerhub actions can my agent take?
44 in total: 35 read, 5 write and 4 destructive, such as “update Portal”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Swaggerhub?
Yes. Actions like “delete Table of Contents Entry” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.
Can my own backend call Swaggerhub too?
Yes. The same Swaggerhub connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Swaggerhub into your agent.
Your users connect Swaggerhub once, under your brand. Your agent gets 44 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan