This server converts Postman collections and requests into type-safe AI agent tools. It:
Generates TypeScript/JavaScript code from Postman collections
Creates tools compatible with multiple AI frameworks (OpenAI, Mistral, Gemini, Anthropic, LangChain, AutoGen)
Produces type-safe code with error handling and response validation
Integrates with Postman API to create AI agent tools
Provides comprehensive type definitions, API integration logic, and documentation in the generated code
Supports JavaScript code generation for AI tools created from Postman collections, including API integration and error handling.
Generates LangChain-compatible tool implementations from Postman API collections, enabling integration with the LangChain framework.
Creates OpenAI-compatible function definitions and tool implementations from Postman API collections, with proper error handling and response validation.
Enables generation of AI agent tools from Postman collections and requests, converting API endpoints into type-safe code for various AI frameworks.
Provides TypeScript code generation for AI tools, with proper type definitions for request/response objects and error handling.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Postman Tool Generation MCP Server create an AI tool from collection 12345-abcde request 67890-fghij in typescript for openai"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP server that generates AI agent tools from Postman collections and requests. This server integrates with the Postman API to convert API endpoints into type-safe code that can be used with various AI frameworks.
Model Context Protocol (MCP) is a new, standardized protocol for managing context between large language models (LLMs) and external systems. In this repository, we provide an installer as well as an MCP Server for Postman Tool Generation API.
This lets you use Claude Desktop, or any MCP Client like Cline, to use natural language to accomplish things on your Postman account, e.g.:
Create an AI tool for: collectionID: 12345-abcde requestID: 67890-fghij typescript openai
Generate TypeScript/JavaScript code from Postman collections
Support for multiple AI frameworks (OpenAI, Mistral, Gemini, Anthropic, LangChain, AutoGen)
Type-safe code generation
Error handling and response validation
Related MCP server: Postman MCP Generator
Install dependencies:
npm installBuild the server:
npm run buildConfigure the MCP settings by adding the following to your Claude settings file (cline_mcp_settings.json):
{
"mcpServers": {
"postman-ai-tools": {
"command": "node",
"args": [
"/path/to/postman-tool-generation-server/build/index.js"
],
"env": {
"POSTMAN_API_KEY": "your-postman-api-key"
},
"disabled": false,
"autoApprove": []
}
}
}The server provides a single tool called generate_ai_tool with the following parameters:
{
collectionId: string; // The Public API Network collection ID
requestId: string; // The public request ID
language: "javascript" | "typescript"; // Programming language to use
agentFramework: "openai" | "mistral" | "gemini" | "anthropic" | "langchain" | "autogen"; // AI framework
}// Using the tool through MCP
const result = await use_mcp_tool({
server_name: "postman-ai-tools",
tool_name: "generate_ai_tool",
arguments: {
collectionId: "your-collection-id",
requestId: "your-request-id",
language: "typescript",
agentFramework: "openai"
}
});The tool generates type-safe code that includes:
Type definitions for request/response
Error handling
API integration
OpenAI function definitions
Documentation and examples
Install dependencies:
npm installMake changes to src/index.ts
Build the server:
npm run buildRestart the Claude app to load the updated server
POSTMAN_API_KEY: Your Postman API key (required)
The server includes comprehensive error handling for:
Invalid parameters
API failures
JSON parsing errors
Network issues
Error responses include detailed messages to help diagnose issues.
Contributions are welcome! Please feel free to submit a Pull Request.
MIT License
Generate code for an AI agent tool using a Postman collection and request
| Name | Required | Description | Default |
|---|---|---|---|
| collectionId | Yes | The Public API Network collection ID | |
| requestId | Yes | The public request ID | |
| language | Yes | Programming language to use | |
| agentFramework | Yes | AI agent framework to use |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool 'generate[s] code' but does not clarify aspects like whether this is a read-only operation, if it requires authentication, potential side effects, or output format. This leaves significant gaps in understanding the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence that efficiently conveys the tool's purpose without unnecessary words. It is front-loaded and every part of the sentence contributes directly to understanding, making it highly concise and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of a code generation tool with no annotations and no output schema, the description is insufficient. It lacks details on what the generated code includes, how it handles errors, or the format of the output, leaving the agent with incomplete information to use the tool effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, so the input schema already documents all parameters thoroughly. The description adds no additional meaning beyond what the schema provides, such as examples or usage context for the parameters. This meets the baseline for high schema coverage but does not enhance parameter understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with specific verbs ('generate code') and resources ('AI agent tool'), specifying the input sources ('Postman collection and request'). It distinguishes what the tool does without ambiguity, making it immediately understandable.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage by mentioning the input sources (Postman collection and request), but it does not provide explicit guidance on when to use this tool versus alternatives, prerequisites, or exclusions. Since there are no sibling tools, the lack of comparative guidance is less critical, but it still lacks detailed context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
With only one tool, there is no possibility of ambiguity or overlap with other tools. The tool's purpose is clearly defined and distinct by default.
A single tool inherently has perfect naming consistency, as there are no other tools to compare it against for patterns or conventions.
One tool is too few for the server's stated purpose of 'Postman Tool Generation,' which implies a broader scope like generating, managing, or testing tools. A single generation tool feels thin and incomplete for this domain.
The tool surface is severely incomplete for the inferred domain of Postman-based tool generation. There are obvious gaps, such as no tools for listing, editing, deleting, or testing generated tools, which limits agent workflows to a single action.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
MCP server for building and testing AI agents with multi-model experimentation and insights.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
MCP server connecting AI agents to 100+ apps (Gmail, Slack, Notion, GitHub) via one-click OAuth.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/giovannicocco/mcp-server-postman-tool-generation'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
