Arlet
Postman

Connect Postman to Copilot Studio

Search, read and write Postman from Copilot Studio. Arlet links the two through one MCP connection and takes care of keys and authentication.

Enable Postman in ArletCopilot Studio connection guide (docs)

Arlet makes Postman's official MCP server available from the AI client you already use. Signing in completes the connection.

The AI can work with workspaces and collections, add and update requests, manage environments, specs and mocks, and run collections. This uses the US region's Minimal configuration (about 40 core tools); the available tools are those provided by Postman's official server.

How to connect Postman to Copilot Studio

  1. 1

    In the Arlet dashboard, open Integrations → Add an integration and choose Postman. Sign in with Link Postman, name the connection and click Create.

  2. 2

    Sign in to Copilot Studio with your work account, create a new agent (or open an existing one), and in the Build tab choose Tools → + → Add → Model Context Protocol (MCP) in the right panel.

  3. 3

    In the Add MCP server form, enter "Arlet" as the Server name, https://mcp.arlet.dev/mcp/ as the Server URL, choose OAuth 2.0 for Authentication and "Dynamic (detected)" for Configuration type, then click Add. No Client ID / Secret is needed.

  4. 4

    On the Select a connection screen, choose Create new connection → Create, then sign in with Google on the Arlet authorization screen and click Allow. Click Add to attach the tool to the agent, then Publish to use it from Microsoft 365 Copilot.

Requires a Microsoft work account and a Copilot Studio license (or trial). MCP is available only for agents using generative orchestration and not in Copilot Studio in Teams.

What you can do

Postman tools that Copilot Studio can call.

  • getWorkspaces

    List workspaces.

  • getCollections

    List the collections in a workspace.

  • getCollection

    Get a collection's structure.

  • createCollection

    Create a collection.

  • createCollectionRequest

    Add a request to a collection.

  • updateCollectionRequest

    Update a request.

  • runCollection

    Run a collection and return the results.

  • getEnvironments

    List environments.

  • createEnvironment

    Create an environment.

  • getAllSpecs

    List API specs.

  • createSpec

    Create an API spec.

  • generateCollection

    Generate a collection from a spec.

  • syncCollectionWithSpec

    Sync a collection with its spec.

  • createMock

    Create a mock server.

  • searchPostmanElements

    Search elements in a workspace.

The tool list follows what Postman's official MCP server provides and may change.

Example uses

  • Run API tests

    Run a collection and summarize failing requests and why.

  • Build a collection from a spec

    Register an OpenAPI spec, generate a collection and set up an environment.

  • Maintain requests

    Add requests for new endpoints to an existing collection with examples and tests.

  • Develop against a mock

    Create a mock server from a spec so front-end work can start early.

Prompts you can use as-is

  • Run the Payments API collection against the staging environment and summarize the failures
  • Register this OpenAPI spec and create a collection and a staging environment for it
  • Add a POST /refunds request to the Payments API collection
  • Create a mock server from the Payments API spec and give me the URL

Use Postman with other AI clients