How is this different from connecting Postman MCP directly?

Connected directly, an agent sees every tool the server exposes and holds the credential itself. Through TrustGate you choose which tools each agent gets, and every call is logged against the agent that made it.

What if the Postman MCP API changes?

We track the Postman MCP schema, so the tool catalogue stays current. Tools you have already allowed keep working, and anything new stays denied until you enable it.

Can I give different agents different Postman tools?

Yes. Access is set per agent: one can get a handful of read tools, another the full set. You grant the whole MCP or single tools within it.

Where can I see what my agents did in Postman?

Every call is logged against the agent that made it, with the tool it used. Activity can be sent on to your own monitoring.

Do I need to run the Postman MCP server myself?

No. TrustGate connects to the Postman MCP server and sits in front of it. Your agent only talks to your TrustGate URL, never to Postman directly.

Connect Postman MCP to your AI agents, securely.

Q: Is Postman MCP secure?

The server itself exposes 26 tools, and some of them can write to your Postman account. Behind TrustGate an agent only sees the tools you allow, requests and responses are inspected, and every call is logged. Anything outside the allowlist is denied before it reaches Postman.

One secured endpoint for every Postman call your AI agents make, scoped per user, inspected, and logged.

Get started for free

Get a demo

Try Postman MCP now

What your agents can ask once Postman MCP is connected.

“List my Postman workspaces”
“Create a collection from this OpenAPI spec”
“Which environments exist in this workspace?”

“Show the requests in this collection”
“Create a mock server from this collection”
“Run this monitor and show the results”

Select the tools your AI agents can call

26 tools from the Postman MCP schema.

Showing 26 tools

getWorkspacesreadGets all workspaces you have access to, optionally filtered by type.
getWorkspacereadGets a workspace and lists the collections, environments, mocks and monitors in it.
createWorkspacewriteCreates a new workspace. Returns 403 if the user does not have permission to create workspaces.
updateWorkspacewriteUpdates the name, type or description of a workspace.
deleteWorkspacehigh riskDeletes a workspace. Linked collections and environments are deleted in all workspaces.
getCollectionsreadLists collections, optionally scoped to a workspace and filtered by name.
getCollectionreadRetrieves a complete collection definition by its UID.
createCollectionwriteCreates a collection in a workspace.
deleteCollectionhigh riskDeletes a collection and everything in it.
createCollectionForkwriteCreates a fork from an existing collection into a workspace.
createCollectionCommentwriteAdds a comment to a collection.
getEnvironmentsreadGets information about all of your environments, optionally scoped to a workspace.
getEnvironmentreadGets a single environment and its variables.
createEnvironmentwriteCreates an environment in a workspace.
deleteEnvironmenthigh riskDeletes an environment.
getMocksreadGets the mock servers, by default only those you created across all workspaces.
getMockreadGets information about a mock server, including its public URL and source collection.
createMockwriteCreates a mock server in a collection.
updateMockwriteUpdates a mock server.
publishMockwritePublishes a mock server, setting its access control to public.
getMonitorsreadGets all monitors, optionally scoped to a workspace.
createMonitorwriteCreates a scheduled monitor for a collection. Monitors cannot be created for collections added to an API definition.
runMonitorwriteRuns a monitor on demand, waits for completion and returns the run results.
getSpecreadGets an API specification and its definition files.
createSpecwriteCreates an API specification in Postman's Spec Hub.
getSpecCollectionsreadGets all of an API specification's generated collections.

What Postman MCP exposes

Postman MCP groups its 26 tools into 5 categories, each with a suggested starting policy.

Category	Covers	Access	Suggested policy
Workspaces	Workspace listing, details, creation, updates and deletion	Read / Write	Require approval for deletes; deleting a workspace removes linked resources everywhere
Collections	Collection listing, details, creation, updates, forks and comments	Read / Write	Audit changes to shared collections
Environments	Environment listing, details, creation, updates and deletion	Read / Write	Treat environment variables as secrets
Mocks & Monitors	Mock servers and scheduled collection monitors, including runs	Read / Write	Approve publishing mocks and triggering monitor runs
Specs	API specifications in Spec Hub and their generated collections	Read / Write	Review generated collections before publishing