Atlas / MCP servers / delano / Postman

PostmanSAFE

Name: Postman
Author: delano

mcp/delano/postman

MCP server by delano · anthropic · claude · mcp · Audited 2026-10-07

⚑ Report / re-scan Source ↗

An MCP server that provides access to Postman.

Verdict

SAFE

Grade

Trust score

89 /100

Exposed tools

109 55r · 40w · 14d

Transport

stdio

License

MIT

Stars

159

Overview

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

[](https://smithery.ai/server/postman-api-server) Version: v0.2.0

An MCP server that provides access to the Postman API. Functionality is based on the official OpenAPI specification. For more information, see the Postman API documentation.

This project is part of the Model Context Protocol (MCP) initiative from Anthropic. For more information, visit the MCP GitHub repository and the announcement on the Anthropic blog.

Skip ahead to install instructions

[!WARNING] This project is currently under active development. Please use with caution and expect breaking changes.

[!NOTE] AI Generated Code. I used Cline v2.2.2 with Claude 3.5 Sonnet (2024-10-22). See docs/README.md for prompts and details about how this code was generated.

Overview
Features
Collections
Environments
APIs
Authentication \& Authorization
Additional Features
Installation
Prerequisites
Steps
Usage
Setting up API Keys
Using Claude Desktop
Using Cline
Using Zed
Documentation
[Project Overv

Read from source at commit 2fe80e634e96OBSERVED · 2026-10-07

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-api-server --env POSTMAN_API_KEY=${POSTMAN_API_KEY} -- npx -y [email protected]

claude-desktop

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

Exposed tools (109)

55 read · 40 write · 14 destructive. Blast radius: 14 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
`Webhooks`	read	List of configured webhooks
`add_api_collection`	write	Add a collection to an API
`add_pan_element`	write	Add element or folder to Private API Network
`analyze_collection`	read	Analyze a Postman collection for potential improvements and best practices
`api_id`	read	ID of the API to document
`collection_id`	read	ID of the collection to analyze
`coverage_level`	read	Desired test coverage level (basic/comprehensive)
`create_api`	write	Create a new API
`create_api_comment`	write	Create a new comment on an API (max 10,000 characters)
`create_api_schema`	write	Create a schema for an API
`create_api_version`	write	Create a new version of an API
`create_collection`	write	Create a new collection in a workspace. Supports Postman Collection v2.1.0 format.
`create_collection_folder`	write	Create a new folder in a collection
`create_collection_request`	write	Create a new request in a collection
`create_collection_response`	write	Create a new response in a collection
`create_environment`	write	Create a new environment in a workspace. Creates in
`create_mock`	write	Create a new mock server. Creates in Personal workspace if workspace not specified.
`create_monitor`	write	Create a new monitor. Cannot create monitors for collections added to an API definition.
`create_server_response`	write	Create a server response. Only one server response can be active at a time.
`create_update_schema_file`	write	Create or update a schema file
`create_webhook`	write	Creates webhook that triggers collection with custom payload
`delete_api`	destructive	Delete an API
`delete_api_comment`	destructive	Delete an API comment
`delete_api_version`	destructive	Delete an API version
`delete_collection`	destructive	Delete a collection
`delete_collection_access_key`	destructive	Delete a collection access key
`delete_collection_folder`	destructive	Delete a folder from a collection
`delete_collection_request`	destructive	Delete a request from a collection
`delete_collection_response`	destructive	Delete a response from a collection
`delete_environment`	destructive	Delete an environment
`delete_mock`	destructive	Delete a mock server
`delete_monitor`	destructive	Delete a monitor
`delete_schema_file`	destructive	Delete a schema file
`delete_server_response`	destructive	Delete a server response
`document_api`	read	Generate documentation for an API based on its collection and schema
`environment_id`	read	ID of the environment to review
`fork_collection`	read	Fork a collection to a workspace
`fork_environment`	write	Create a fork of an environment in a workspace
`format`	read	Documentation format (markdown/html)
`get_accounts`	read	Gets Postman billing account details for the given team
`get_api`	read	Get details of a specific API
`get_api_collection`	read	Get a specific collection from an API
`get_api_comments`	read	Get comments for an API
`get_api_schema`	read	Get a specific schema from an API
`get_api_schema_files`	read	Get files in an API schema
`get_api_tags`	read	Get tags for an API
`get_api_version`	read	Get a specific version of an API
`get_api_versions`	read	Get all versions of an API
`get_authenticated_user`	read	Get authenticated user information
`get_collection`	read	Get details of a specific collection
`get_collection_folder`	read	Get details of a specific folder in a collection
`get_collection_forks`	read	Get a list of collection forks
`get_collection_request`	read	Get details of a specific request in a collection
`get_collection_response`	read	Get details of a specific response in a collection
`get_collection_roles`	read	Get roles for a collection
`get_environment`	read	Get details of a specific environment
`get_environment_forks`	read	Get a list of environment forks
`get_mock`	read	Get details of a specific mock server
`get_mock_call_logs`	read	Get mock call logs. Maximum 6.5MB or 100 call logs per API call. Retention period based on Postman plan.
`get_monitor`	read	Get details of a specific monitor
`get_schema_file_contents`	read	Get contents of a schema file
`get_server_response`	read	Get a specific server response
`get_tagged_elements`	read	Get elements by tag
`get_task_status`	read	Get status of an asynchronous task
`get_user_info`	read	Get information about the authenticated user
`get_workspace`	read	Get details of a specific workspace
`get_workspace_roles`	read	Get roles for a specific workspace
`get_workspace_tags`	read	Get workspace tags
`list_account_invoices`	read	Gets all invoices for a Postman billing account filtered by status
`list_apis`	read	List all APIs in a workspace
`list_collection_access_keys`	read	List collection access keys with optional filtering by collection ID
`list_collections`	read	Show all collections across workspaces
`list_environments`	read	Show all environments and their variables
`list_mocks`	read	Show all mock servers and their configurations
`list_monitors`	read	Show all active monitors and their status
`list_pan_elements`	read	Get all elements and folders in Private API Network
`list_server_responses`	read	Get all server responses for a mock
`list_workspace_roles`	read	Get all available workspace roles based on team\
`list_workspaces`	read	Show all available workspaces and their details
`merge_collection_fork`	write	Merge a forked collection back into its parent
`merge_environment_fork`	write	Merge a forked environment back into its parent
`patch_collection`	write	Partially update a collection. Only updates provided fields.
`publish_mock`	write	Publish mock server (sets Access Control to public)
`pull_collection_changes`	read	Pull changes from parent collection into forked collection
`pull_environment`	read	Pull changes from parent environment into forked environment
`remove_pan_element`	destructive	Remove element or folder from Private API Network
`resolve_comment_thread`	read	Resolves a comment and any associated replies
`review_environment`	read	Review environment variables for security and completeness
`run_monitor`	write	Run a monitor. For async=true, response won\
`suggest_tests`	read	Suggest test cases for API endpoints in a collection
`sync_collection_with_schema`	write	Sync a collection with its schema
`transfer_collection_items`	write	Transfer items between collections
`unpublish_mock`	read	Unpublish mock server (sets Access Control to private)
`update_api`	write	Update an existing API
`update_api_comment`	write	Update an existing API comment (max 10,000 characters)
`update_api_tags`	write	Update tags for an API
`update_api_version`	write	Update an API version
`update_collection`	write	Update an existing collection. Full collection replacement with maximum size of 20 MB.
`update_collection_folder`	write	Update a folder in a collection. Acts like PATCH, only updates provided values.
`update_collection_request`	write	Update a request in a collection. Cannot change request folder.
`update_collection_response`	write	Update a response in a collection. Acts like PATCH, only updates provided values.
`update_collection_roles`	write	Update collection roles (requires EDITOR role)
`update_environment`	write	Update an existing environment. Only include variables that need to be modified.
`update_mock`	write	Update an existing mock server
`update_monitor`	write	Update an existing monitor
`update_pan_element`	write	Update element or folder in Private API Network
`update_server_response`	write	Update a server response
`update_workspace_roles`	write	Update workspace roles for users and groups (limited to 50 operations per call)
`update_workspace_tags`	write	Update workspace tags

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 (6 observation(s))
Network: declared (5 observation(s))
Shell: none-observed
Dependencies: not all pinned
Secrets in source: none-found

Findings (10)

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

delete_api, delete_api_comment, delete_api_version, delete_collection, delete_collection_access_key, delete_collection_folder, delete_collection_request, delete_collection_response, delete_environment

Why it matters. 14 tool(s) can delete or overwrite

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