The Postman Plugin provides a single, simple install for Claude Code. It provides full API lifecycle management, and best practices when working with Postman APIs.
Install from Anthropic's official plugin marketplace.
In Claude Code:
/plugin install postman@claude-plugins-official
Or from the terminal:
claude plugin install postman@claude-plugins-official
claude plugin install github:Postman-Devrel/postman-claude-code-plugin
git clone https://github.com/Postman-Devrel/postman-claude-code-plugin.git
cd your-api-project/
claude --plugin-dir /path/to/postman-claude-code-plugin
claude
/postman:setup
export POSTMAN_API_KEY=PMAK-your-key-here
If you use an API key, add it to your shell profile (~/.zshrc or ~/.bashrc) to persist across sessions. Get one at go.postman.co/settings/me/api-keys.
That's it. The plugin auto-configures the Postman MCP Server, verifies your connection, and lists your workspaces. You're ready to go.
| Command | What It Does |
|---|---|
/postman:setup | Configure API key, verify connection, select workspace |
/postman:sync | Create or update Postman collections from OpenAPI specs |
/postman:search | Find APIs across your org's resources, your workspaces, and the public Postman network |
/postman:context | Fetch real API definitions, generate and maintain typed client code |
/postman:test | Run collection tests, diagnose failures, suggest fixes |
/postman:mock | Create mock servers for frontend development |
/postman:docs | Generate, improve, and publish API documentation |
/postman:security | Security audit against OWASP API Top 10 |
/postman:learn | Search the Postman Learning Center for how-to guidance and suggested workflows (Full mode) |
"Sync my OpenAPI spec with Postman"
→ Detects local spec, creates/updates collection, sets up environment
"Generate a TypeScript client for the payments API"
→ Reads your Postman collection, detects project language, writes typed code
"Is there an endpoint that returns user emails?"
→ Searches across your org's collections, drills into endpoint details, shows response shapes
"Run the tests for my User API collection"
→ Executes collection, parses results, diagnoses failures, suggests code fixes
"Create a mock for frontend development"
→ Generates missing examples, creates mock, provides integration config
"Run a security audit on my API"
→ 20+ checks including OWASP Top 10, severity scoring, remediation guidance
"Is my API ready for AI agents?"
→ 48 checks across 8 pillars, scored 0-100, prioritized fix recommendations
You don't need to remember command names. Claude matches your intent to the right command or skill natively:
/postman:sync/postman:securityThe built-in readiness analyzer evaluates APIs for AI agent compatibility across 8 pillars:
| Pillar | What It Checks |
|---|---|
| Metadata | operationIds, summaries, descriptions, tags |
| Errors | Error schemas, codes, retry guidance |
| Introspection | Parameter types, required fields, examples |
| Naming | Consistent casing, RESTful paths |
| Predictability | Response schemas, pagination, date formats |
| Documentation | Auth docs, rate limits |
| Performance | Rate limit headers, caching, bulk endpoints |
| Discoverability | OpenAPI version, server URLs |
70%+ with no critical failures = Agent-Ready.
/postman:setup, or set a POSTMAN_API_KEY environment variableThe plugin bundles a .mcp.json file that auto-configures the Postman MCP Server when installed. All commands communicate with Postman through MCP tools. No scripts, no dependencies, pure MCP.
By default the plugin connects to the full Postman MCP Server (100+ tools). Recent Claude Code versions load MCP tool schemas on demand, so the full server adds little context overhead. If you're on an older client or want a lighter session, set POSTMAN_MCP_MODE before starting Claude Code to pick a smaller server mode:
export POSTMAN_MCP_MODE=minimal # ~42 CRUD tools; code-generation (context) tools unavailable
export POSTMAN_MCP_MODE=code # ~24 read-only tools for API discovery and client code generation
Apache-2.0
The Postman Plugin provides a single, simple install for Claude Code. It provides full API lifecycle management, and best practices when working with Postman APIs.
Install from Anthropic's official plugin marketplace.
In Claude Code:
/plugin install postman@claude-plugins-official
Or from the terminal:
claude plugin install postman@claude-plugins-official
claude plugin install github:Postman-Devrel/postman-claude-code-plugin
git clone https://github.com/Postman-Devrel/postman-claude-code-plugin.git
cd your-api-project/
claude --plugin-dir /path/to/postman-claude-code-plugin
claude
/postman:setup
export POSTMAN_API_KEY=PMAK-your-key-here
If you use an API key, add it to your shell profile (~/.zshrc or ~/.bashrc) to persist across sessions. Get one at go.postman.co/settings/me/api-keys.
That's it. The plugin auto-configures the Postman MCP Server, verifies your connection, and lists your workspaces. You're ready to go.
| Command | What It Does |
|---|---|
/postman:setup | Configure API key, verify connection, select workspace |
/postman:sync | Create or update Postman collections from OpenAPI specs |
/postman:search | Find APIs across your org's resources, your workspaces, and the public Postman network |
/postman:context | Fetch real API definitions, generate and maintain typed client code |
/postman:test | Run collection tests, diagnose failures, suggest fixes |
/postman:mock | Create mock servers for frontend development |
/postman:docs | Generate, improve, and publish API documentation |
/postman:security | Security audit against OWASP API Top 10 |
/postman:learn | Search the Postman Learning Center for how-to guidance and suggested workflows (Full mode) |
"Sync my OpenAPI spec with Postman"
→ Detects local spec, creates/updates collection, sets up environment
"Generate a TypeScript client for the payments API"
→ Reads your Postman collection, detects project language, writes typed code
"Is there an endpoint that returns user emails?"
→ Searches across your org's collections, drills into endpoint details, shows response shapes
"Run the tests for my User API collection"
→ Executes collection, parses results, diagnoses failures, suggests code fixes
"Create a mock for frontend development"
→ Generates missing examples, creates mock, provides integration config
"Run a security audit on my API"
→ 20+ checks including OWASP Top 10, severity scoring, remediation guidance
"Is my API ready for AI agents?"
→ 48 checks across 8 pillars, scored 0-100, prioritized fix recommendations
You don't need to remember command names. Claude matches your intent to the right command or skill natively:
/postman:sync/postman:securityThe built-in readiness analyzer evaluates APIs for AI agent compatibility across 8 pillars:
| Pillar | What It Checks |
|---|---|
| Metadata | operationIds, summaries, descriptions, tags |
| Errors | Error schemas, codes, retry guidance |
| Introspection | Parameter types, required fields, examples |
| Naming | Consistent casing, RESTful paths |
| Predictability | Response schemas, pagination, date formats |
| Documentation | Auth docs, rate limits |
| Performance | Rate limit headers, caching, bulk endpoints |
| Discoverability | OpenAPI version, server URLs |
70%+ with no critical failures = Agent-Ready.
/postman:setup, or set a POSTMAN_API_KEY environment variableThe plugin bundles a .mcp.json file that auto-configures the Postman MCP Server when installed. All commands communicate with Postman through MCP tools. No scripts, no dependencies, pure MCP.
By default the plugin connects to the full Postman MCP Server (100+ tools). Recent Claude Code versions load MCP tool schemas on demand, so the full server adds little context overhead. If you're on an older client or want a lighter session, set POSTMAN_MCP_MODE before starting Claude Code to pick a smaller server mode:
export POSTMAN_MCP_MODE=minimal # ~42 CRUD tools; code-generation (context) tools unavailable
export POSTMAN_MCP_MODE=code # ~24 read-only tools for API discovery and client code generation
Apache-2.0