Atlas / MCP servers / salehkhatri / Postman

PostmanSAFE

Name: Postman
Author: salehkhatri

mcp/salehkhatri/postman-2

MCP server by salehkhatri · api · mcp · mcp server · Audited 2026-10-08

A Model Context Protocol (MCP) server that provides seamless integration with the Postman API. This package enables AI assistants and applications to interact with Postman workspaces, collections, requests, environments, and folders programmatically.

Verdict

SAFE

Grade

Trust score

89 /100

Exposed tools

19 6r · 9w · 4d

Transport

stdio

License

MIT

Stars

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

A Model Context Protocol (MCP) server that provides seamless integration with the Postman API. This package enables AI assistants and applications to interact with Postman workspaces, collections, requests, environments, and folders programmatically.

[](https://www.npmjs.com/package/postman-mcp) [](https://opensource.org/licenses/MIT)

🚀 Features

📁 Workspace Management

List all workspaces
Get detailed workspace information
Create new workspaces (personal/team)
Update workspace metadata

📚 Collection Management

List collections within workspaces
Get collection details with full structure
Create new collections
Update collection metadata and variables
Delete collections

🔧 Request Management

Add new HTTP requests to collections
Update existing requests (method, URL, headers, body)
Move requests between folders
Delete requests
Support for all HTTP methods (GET, POST, PUT, PATCH, DELETE, HEAD, OPTIONS)

🌍 Environment Management

List environments in workspaces
Get environment details and variables
Create new environments with variables
Update environment variables
Delete environments
Support for secret, default, and custom variable types

📂 Folder Organization

Create nested folder structures
Organize requests within folders
Support for hierarchical folder paths

⚙️ Setup

1. Get Your Postman API Key

Go to Postman Account Settings
Click "Generate API Key"
Give it a name and copy the generated key

2. MCP Configuration

For Claude Desktop

Add to your Claude Desktop configuration file (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
"mcpServers": {
"postman": {
"command": "npx",
"args": ["postman-mcp"],
"env": {
"POSTM

Read from source at commit 509733ecaa76OBSERVED · 2026-10-08

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code

claude mcp add postman-mcp --env POSTMAN_API_KEY=${POSTMAN_API_KEY} -- npx -y [email protected]

claude-desktop

{
  "mcpServers": {
    "postman-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "POSTMAN_API_KEY": "${POSTMAN_API_KEY}"
      }
    }
  }
}

Exposed tools (19)

6 read · 9 write · 4 destructive. Blast radius: 4 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.

Tool	Risk	Description
`add_request`	write	Add a new request to a collection
`create_collection`	write	Create a new collection
`create_environment`	write	Create a new environment
`create_folder`	write	Create a new folder in a collection
`create_workspace`	write	Create a new workspace
`delete_collection`	destructive	Delete a Postman collection
`delete_environment`	destructive	Delete an existing environment
`delete_folder`	destructive	Delete a folder from a collection
`delete_request`	destructive	Delete a request from a collection
`get_collection`	read	Get detailed information about a specific collection
`get_environment`	read	Get detailed information about a specific environment
`get_workspace`	read	Get detailed information about a specific workspace
`list_collections`	read	List all collections in a workspace
`list_environments`	read	List all environments
`list_workspaces`	read	List all workspaces
`update_collection`	write	Update collection metadata (name, description, variables)
`update_environment`	write	Update an existing environment
`update_request`	write	Update an existing request in a collection
`update_workspace`	write	Update an existing workspace

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

Layer	What it checks	Result
L0	Provenance & inventory	PASS
L1	Static analysis of the code	PASS
L2	Instruction surface (what it tells the agent)	PASS
L3	Class-specific surface	WARN
L4	Behavioural (sandbox)	SKIPPED

What the source does

Filesystem: declared (1 observation(s))
Network: declared (1 observation(s))
Shell: none-observed
Dependencies: not all pinned
Secrets in source: none-found

Findings (2)

MEDIUMFilesystem / path · mcp.destructive_tools · CWE-22, CWE-59

delete_collection, delete_environment, delete_folder, delete_request

Why it matters. 4 tool(s) can delete or overwrite

Fix. prefer a read-only mode or scoped tokens; the page states the blast radius

LOWSupply chain · supply.unpinned · CWE-829, CWE-1357

package.json

@modelcontextprotocol/sdk, axios, dotenv, zod, zod-to-json-schema, @types/node, tsx, typescript

Why it matters. 8 dependency range(s) float

Fix. pin exact versions or ship a lockfile

Gates applied: no_behavioural_pass.

Audited 2026-10-08 · audit v0.4.1 · source sha 509733ecaa76full audit observations/trust-audit/mcp-server/salehkhatri__postman-2.json · Report an issue / request a re-scan

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

Date	Source	Verdict	Grade	Score	Change
2026-10-08	`509733ecaa76`	SAFE	B	89	first audit

Questions

What is the Postman MCP server?

What tools does Postman expose?

19 in total: 6 read-only, 9 that write, and 4 that can delete or overwrite (delete_collection, delete_environment, delete_folder, delete_request). Every one is listed on this page with its risk.

Is Postman safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 4 of its tools can destroy data, so scope the token you give it to what you actually need.

What credentials does Postman need?

It reads POSTMAN_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does Postman run?

It speaks stdio, so it runs as a local process your client starts. It is published on npm as postman-mcp at 1.0.3.

How current is this page?

The grade is for one exact copy of the source (509733ecaa76), read on 2026-10-08. The repository is watched and re-audited when it changes.

Source	salehkhatri/postman-mcp
npm	`postman-mcp@1.0.3`
Transports	stdio
Credentials it reads	`POSTMAN_API_KEY`
License	MIT
Activity	pushed 230d ago