Provider REST API

16 actions

Connect Claude to Postman

Read Postman workspaces, collections and environments, and run the monitors that test an API on a schedule. Toolspoke puts 16 of its actions behind one MCP endpoint that Claude, Cursor, and Codex all speak.

Connect View pricing

Connection: Provider REST API
Authentication: API key
Actions exposed: 16
What a call bills: Nothing
Adapter: Maintained by Toolspoke

Connected in three steps

1
Install Postman
Open the marketplace in your workspace, add Postman to the project your agents work in, and it appears on the gateway immediately.
2
Connect the credential
Authenticate with api key. Where to get one, and what it has to be able to reach, is the next section.
3
Point your agent at the gateway
Give your client one address, https://toolspoke.com/mcp. Claude Code takes it as a command, Claude and Claude Desktop add it as a custom connector, and Cursor, Codex and VS Code each read it from a config file of their own.

.mcp.json

{
  "mcpServers": {
    "toolspoke": {
      "type": "http",
      "url": "https://toolspoke.com/mcp"
    }
  }
}

One block covers every tool you have installed. Postman shows up in the client as soon as your policy allows it, and so does everything else you install later.

Where the address goes, per client

Claude Code: Run it in your project, then /mcp to sign in
claude mcp add --transport http toolspoke https://toolspoke.com/mcp
Claude and Claude Desktop: Settings, then Connectors, then Add custom connector
https://toolspoke.com/mcp
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json for one project
{ "mcpServers": { "toolspoke": { "url": "https://toolspoke.com/mcp" } } }
Codex: ~/.codex/config.toml
[mcp_servers.toolspoke] url = "https://toolspoke.com/mcp"
VS Code: .vscode/mcp.json, or the MCP: Add Server command
{ "servers": { "toolspoke": { "type": "http", "url": "https://toolspoke.com/mcp" } } }

What Postman asks for

API key. You provide it once, when you install the connector. Toolspoke encrypts it at rest and decrypts it only for the length of a single call, and the gateway attaches it to the outbound request itself, so it is never part of the arguments an agent sends.

API keyRequired: Postman → your avatar → Settings → API keys → Generate API Key. The key acts as you, in every workspace you can open.; PMAK-…

What Claude can do in Postman

16 actions, each one declared and named by the connector rather than discovered at runtime. A workspace policy grants a person all of them, a hand-picked selection, everything on the read side, everything on the write side, or none.

Reads: 10Reads
Writes: 4Writes
Destructive: 2Destructive

Reads

Fetches data and changes nothing.

get_me
Return the user the API key belongs to, with their team and API usage limits.
list_workspaces
List the workspaces this key can open, with the workspace id the collection, environment and monitor lists take. Also the install's connection test - it proves the key reaches workspace data, not just an account.
get_workspace
Retrieve one workspace with the collections, environments, monitors, mocks and APIs in it.
list_collections
List the collections in one workspace, with each collection's uid.
get_collection
Retrieve one collection in full - its folders, requests, scripts, variables and auth settings. Collections often carry tokens in headers or variables, so the response is not written to the audit log.
get_collection_request
Retrieve one request from a collection - method, URL, headers, body and scripts.
list_environments
List environments, optionally in one workspace, with each environment's uid. Values are not included; get_environment returns them.
get_environment
Retrieve one environment with its variables and their values. Environment values are usually secrets - base URLs, API keys, passwords - so the response is not written to the audit log.
list_monitors
List monitors - collections Postman runs on a schedule against a live API - with each monitor's uid and whether it is active.
get_monitor
Retrieve one monitor with its schedule, collection, environment and the result of its last run.

Writes

Creates or updates something on the other side.

run_monitor
Run a monitor now and return its results - passed and failed assertions, response times and errors. A write rather than destructive: it does exactly what the monitor's own schedule already does, against the API it already targets. Runs longer than 300 seconds return 202 before they finish; set async to true for a long collection and read the result later with get_monitor.
create_collection
Create a collection in a workspace from a Postman Collection v2.1 document. delete_collection undoes it.
create_environment
Create an environment in a workspace. Values are masked in the audit log.
update_environment
Replace an environment's name and variables. The variables sent become the whole list - any variable left out is removed. Values are masked in the audit log.

Destructive

Deletes or permanently alters something. Worth granting on purpose.

delete_collection
Delete a collection. Destructive because it removes the collection for everyone in the workspace, and any monitor or mock built on it stops working.
delete_environment
Delete an environment and every value in it. Destructive because the values - often the only copy of a secret someone pasted in - cannot be recovered.

What it will not do

Enforced by the gateway rather than left to convention, which is why each of these can be stated flatly.

It cannot call anything else: The 16 actions above are the whole of it. A call to any other name is refused before it reaches Postman rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time.
It reaches no further than your credential: Toolspoke holds no access to Postman of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either.
It never hears from Postman: Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Postman. An agent has to ask.
It does not smooth over provider limits: Toolspoke does not retry, queue or back off around Postman's own rate limits. A call that Postman refuses comes back to the agent as a failed call.

Before you connect it

What can Claude do in Postman?

16 named actions: 10 that only read, 4 that write and 2 that delete or permanently alter something. They include get_me, list_workspaces and get_workspace. Nothing outside that list is reachable: the connector declares each operation by name rather than proxying whatever an agent asks for.

What credentials does the Postman connector need?

API key. The connector asks for api key. Values are encrypted at rest and attached to the outbound request by the gateway, so they are never part of the arguments an agent sends and never reach the audit log.

Does the Postman connector work with Cursor and Codex, or only Claude?

Any client that speaks MCP, and every one of them gets the same 16 actions. There is a single address, https://toolspoke.com/mcp. Claude Code adds it with claude mcp add --transport http, Claude and Claude Desktop take it as a custom connector in settings, Cursor reads it from .cursor/mcp.json, Codex from ~/.codex/config.toml, and VS Code from .vscode/mcp.json. Each of them signs in to the gateway itself, so there is no key to paste.

What does the Postman connector not do?

The 16 actions above are the whole of it. A call to any other name is refused before it reaches Postman rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time. Toolspoke holds no access to Postman of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either. Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Postman. An agent has to ask. Toolspoke does not retry, queue or back off around Postman's own rate limits. A call that Postman refuses comes back to the agent as a failed call.

Can I limit which actions an agent can call?

Yes, in two places. The project switches Postman's actions on and off one at a time, for everyone in the project at once, and the screen groups them by read, write and destructive so turning off everything that deletes is one click. An individual agent key can then be narrowed further, to particular toolkits in a project and to particular actions in a toolkit. Whatever it was granted, a key never reaches a project its owner cannot.

What gets recorded when an agent calls Postman?

Every attempt, with the agent that made it and the person that agent belongs to, the full request payload, the response payload, the status, the duration, and what the call cost in sandbox time and model tokens. Values whose key names a secret are masked out before the record is shown to anyone. An operation the connector marks as not retained never has its response body written at all, so the gateway keeps no second copy of what was read.

More developer tools connectors

Browse all of them