Postmancer
An experimental MCP server Rest Client intended to be a replacement of tools postman & insomnia
hijaz
README
Postmancer
A standalone MCP server for API testing and management, allowing AI assistants to interact with RESTful APIs through natural language.
Overview
Postmancer is an MCP (Model Context Protocol) server that enables AI assistants like Claude to make HTTP requests, manage collections of API endpoints, and test API responses. It provides similar functionality to tools like Postman or Insomnia but designed specifically for AI assistants.
Features
- Make HTTP requests to any REST API
- Save and organize requests in collections
- Set and use environment variables with variable substitution
- Multiple authentication methods (Basic, Bearer, API Key, OAuth2)
- Request/response history and testing
Quick Start
Installation
# Install globally
npm install -g postmancer
# Or run directly with npx
npx postmancer
Using with Claude Desktop
Add this to your Claude Desktop configuration file:
- Windows:
%USERPROFILE%\.claude\claude_desktop_config.json
- macOS/Linux:
~/.claude/claude_desktop_config.json
{
"mcpServers": {
"postmancer": {
"command": "npx",
"args": ["-y", "postmancer"],
"env": {
"LOG_LEVEL": "info"
}
}
}
}
Using with Docker
docker run -i --rm \
--mount type=bind,src=/path/to/collections,dst=/data/collections \
postmancer
Available Tools
Postmancer provides the following tools to AI assistants:
- http_request - Send HTTP requests to any URL
- list_collections - View all your saved API collections
- list_requests - View all requests in a collection
- save_request - Save a request to a collection
- request_from_collection - Execute a saved request
- set_environment_variable - Set variables for request templates
- get_environment_variables - View all environment variables
Configuration
Configure Postmancer with these environment variables:
COLLECTIONS_PATH
: Path to store collections (default: ~/.postmancer)LOG_LEVEL
: Logging level (debug, info, warn, error) (default: info)POSTMANCER_ENCRYPTION_KEY
: Secret key used to encrypt credentials and tokens (generates a random key if not provided)ENCRYPTION_KEY
: Secret key used to encrypt environment variables marked as secrets (uses default key if not provided)
For security in production environments, it's strongly recommended to set these encryption keys rather than using the defaults.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
MCP Package Docs Server
Facilitates LLMs to efficiently access and fetch structured documentation for packages in Go, Python, and NPM, enhancing software development with multi-language support and performance optimization.
Claude Code MCP
An implementation of Claude Code as a Model Context Protocol server that enables using Claude's software engineering capabilities (code generation, editing, reviewing, and file operations) through the standardized MCP interface.
@kazuph/mcp-taskmanager
Model Context Protocol server for Task Management. This allows Claude Desktop (or any MCP client) to manage and execute tasks in a queue-based system.
Linear MCP Server
Enables interaction with Linear's API for managing issues, teams, and projects programmatically through the Model Context Protocol.
mermaid-mcp-server
A Model Context Protocol (MCP) server that converts Mermaid diagrams to PNG images.
Jira-Context-MCP
MCP server to provide Jira Tickets information to AI coding agents like Cursor

Linear MCP Server
A Model Context Protocol server that integrates with Linear's issue tracking system, allowing LLMs to create, update, search, and comment on Linear issues through natural language interactions.

Sequential Thinking MCP Server
This server facilitates structured problem-solving by breaking down complex issues into sequential steps, supporting revisions, and enabling multiple solution paths through full MCP integration.