PostmanSAFE
Postman MCP Server — connect AI agents (Claude Code, Cursor, VS Code Copilot, Gemini CLI) to your Postman collections, OpenAPI specs, and environments via Model Context Protocol (MCP)
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
The Postman MCP Server implements the Model Context Protocol (MCP) to connect AI agents and coding assistants — including Claude Code, Cursor, VS Code Copilot, GitHub Copilot CLI, and Gemini CLI — directly to your Postman workspaces, collections, specifications, and environments.
Postman also offers the server as an npm package.
For the full installation guide with agent-specific setup, see Postman's MCP Server product page.
Postman MCP Server collection
The Postman MCP Server collection is the quickest way to explore, test, and connect to the Postman MCP Server. Use it to:
- Browse the complete list of available tools across all configurations.
- Connect to and test the remote server — Full and Minimal.
- Connect to and test the local server.
Tool configurations
- Minimal — (Default) Only includes essential tools for basic Postman operations. Ideal for users who want to modify a single Postman element, such as collections, workspaces, or environments.
- Code — Includes tools to generate high-quality, well-organized client code from public and internal API definitions. Ideal for users who need to consume APIs or get API context to their agents.
- Full — Includes all available Postman API tools (100+ tools). Ideal for users who engage in advanced collaboration and Postman's Enterprise features.
- Learn — Searches Postman Docs for guides, tutorials, an
b1dcc55d1a3cOBSERVED · 2026-10-05Connect
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 mcp add postman-mcp-server --env POSTMAN_API_KEY=${POSTMAN_API_KEY} --env POSTMAN_API_KEY=${POSTMAN_API_KEY} --env POSTMAN_API_KEY=${POSTMAN_API_KEY} --env POSTMAN_API_KEY=${POSTMAN_API_KEY} -- npx -y @postman/[email protected]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 | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (2 observation(s))
- Network
- declared (5 observation(s))
- Shell
- declared (5 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (10)
.dxtignore
.prettierrc.js
import { RUNNER_ACCEPT_HEADER } from '../../constants.js';import { env } from '../../env.js';import { PostmanAPIClient } from '../../clients/postman.js';import type { ServerContext } from '../../tools/utils/toolHelpers.js';import packageJson from '../../../package.json' assert { type: 'json' };@modelcontextprotocol/sdk, dotenv, newman, nunjucks, uuid, zod, @eslint/js, @types/node
@modelcontextprotocol/sdk, dotenv, newman, nunjucks, uuid, zod, @eslint/js, @types/node
Gates applied: no_behavioural_pass.
b1dcc55d1a3cfull audit observations/trust-audit/mcp-server/postmanlabs__postman-3.json · Report an issue / request a re-scanAudit 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 |
|---|---|---|---|---|---|
| 2026-10-05 | b1dcc55d1a3c | SAFE | B | 89 | first audit |
Questions
What is the Postman MCP server?
Postman MCP Server — connect AI agents (Claude Code, Cursor, VS Code Copilot, Gemini CLI) to your Postman collections, OpenAPI specs, and environments via Model Context Protocol (MCP)
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.
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 and streamable-http, so it runs as a local process your client starts. It is published on npm as @postman/postman-mcp-server at 2.13.0.
How current is this page?
The grade is for one exact copy of the source (b1dcc55d1a3c), read on 2026-10-05. The repository is watched and re-audited when it changes.