Postman for AI agents
Postman is an API platform for building, testing, and documenting APIs with collaboration features for teams. Developers use it to design, test, and monitor APIs throughout their lifecycle. 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 Postman.
Create a request in a collection
Add a new API request to a collection so it can be tested and shared with the team.
Check a monitor's run history read-only
Look up a monitor's recent runs to confirm an API is passing its scheduled checks.
Delete a collection with approval
Remove an unused collection only after the team confirms it is no longer needed.
135 Postman actions, graded by risk.
Every Postman action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
60Look things up. Allowed by default.
- postman.get_an_apiGet API Information
- postman.get_a_specGet API Specification
- postman.get_accountsGet Billing Account Details
- postman.get_a_folderGet Folder Information
- postman.get_all_apisGet All APIs
- postman.get_a_schemaGet API Schema
- postman.get_all_specsGet All API Specifications
- postman.get_a_monitorGet Monitor Information
- postman.get_a_requestGet Request Information
- postman.get_all_groupsGet All Groups
- postman.get_a_responseGet Response Information
- postman.get_a_spec_fileGet Spec File Contents
- postman.get_a_team_userGet Team User
- postman.get_a_workspaceGet Workspace Details
- postman.get_all_monitorsGet All Monitors
- postman.get_all_versionsGet All API Versions
write
57Create and change things. Allow, or ask the user first.
- postman.create_an_apiCreate an API
- postman.create_a_specCreate a Spec
- postman.update_an_apiUpdate an API
- postman.create_a_fork2Create Environment Fork
- postman.create_a_folderCreate a Folder
- postman.create_a_schemaCreate API Schema
- postman.update_a_folderUpdate a Folder
- postman.create_a_monitorCreate a Monitor
- postman.create_a_requestCreate Request in Collection
- postman.create_a_webhookCreate a Webhook
- postman.create_relationsCreate API Version Relations
- postman.update_a_monitorUpdate a Monitor
- postman.update_a_requestUpdate Request in Collection
- postman.create_a_responseCreate a Response
- postman.update_a_responseUpdate a Response
- postman.create_a_spec_fileCreate Spec File
destructive
18Delete, cancel or archive. Ask first, or deny outright.
- postman.delete_an_apiDelete an API
- postman.delete_a_specDelete a Spec
- postman.delete_monitorDelete Monitor
- postman.delete_a_folderDelete a Folder
- postman.delete_a_responseDelete a Response
- postman.delete_a_spec_fileDelete Spec File
- postman.delete_a_workspaceDelete a Workspace
- postman.delete_a_collectionDelete a Collection
- postman.delete_a_schema_fileDelete a Schema File
- postman.delete_an_environmentDelete an environment
- postman.delete_an_apis_commentDelete an API's Comment
- postman.delete_a_folders_commentDelete a Folder's Comment
- postman.delete_a_server_responseDelete Mock Server Response
- postman.delete_a_requests_commentDelete a Request's Comment
- postman.delete_a_responses_commentDelete a Response's Comment
- postman.delete_a_collections_commentDelete a collection's comment
Postman in three steps.
- 01Your users connect PostmanThey add their Postman api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create an API” can wait for the user, and “delete an API” can be denied outright.
- 03Any agent can actYour agent calls Postman through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('postman', { read: 'allow', write: 'ask', // create_an_api destructive: 'deny', // delete_an_api }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Postman connects.
Users add their Postman 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 Postman 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 Postman from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Postman and Arc0, answered.
Can I use Postman with Claude, ChatGPT or Cursor?
Yes. Connect Postman 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 Postman actions you allow.
How do users connect Postman?
Users add their Postman 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 Postman actions can my agent take?
135 in total: 60 read, 57 write and 18 destructive, such as “create an API”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Postman?
Yes. Actions like “delete an API” 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 Postman too?
Yes. The same Postman connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Postman into your agent.
Your users connect Postman once, under your brand. Your agent gets 135 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan