Payman Documentation MCP Server
Official# Payman AI Documentation MCP Server
MCP server that provides easy access to Payman AI's documentation and helps developers build integrations more efficiently.
## Overview
This repository contains the source code for a Payman documentation MCP server. This server allows AI assistants like Claude or Cursor to access Payman's documentation to help developers with their integration questions. By running this server locally, you can enhance your AI assistant's ability to provide accurate and helpful information about Payman's capabilities.
## Prerequisites
- [Node.js](https://nodejs.org/) (v14 or higher)
- [npm](https://www.npmjs.com/) or [yarn](https://yarnpkg.com/)
- Git
## Installation
1. Clone the repository:
```bash
git clone https://github.com/PaymanAI/payman-doc-mcp-server
```
2. Navigate to the project directory:
```bash
cd payman-doc-mcp-server
```
3. Install dependencies:
```bash
npm install
# OR
yarn install
```
## Building the Project
Build the TypeScript code into JavaScript:
```bash
npm run build
# OR
yarn build
```
## Checking Server
Check if the server is properly setup:
```bash
node /ABSOLUTE/PATH/TO/PARENT/FOLDER/payman-doc-mcp-server/build/index.js
```
If everything is good, you can now add the Payman MCP server to any client.
- For Claude Desktop: [Here](https://modelcontextprotocol.io/quickstart/server#claude-for-desktop-integration-issues)
- For Cursor: [Here](https://docs.cursor.com/context/model-context-protocol)
TDQS
Scored across 5 tools
The tools have overlapping purposes that could cause confusion. For example, 'get-documentation' and 'search-documentation' both retrieve documentation content, and 'get-sdk-help' and 'solve-problem' both address integration issues. However, the descriptions provide some differentiation in scope (e.g., specific topics vs. search, SDK usage vs. general issues), which helps mitigate complete ambiguity.
All tool names follow a consistent verb_noun pattern with hyphens, such as 'get-code-examples' and 'search-documentation'. This uniformity makes the set predictable and easy to parse, with no deviations in naming conventions across the five tools.
With 5 tools, the count is reasonable for a documentation-focused server, providing a focused set without being overly sparse or bloated. It covers key areas like examples, documentation retrieval, and problem-solving, though it might benefit from one or two more specialized tools (e.g., for API reference or version-specific info) to be ideal.
The tool set covers core documentation needs: retrieving examples, documentation, SDK help, searching, and solving problems. Minor gaps exist, such as no tools for updating documentation, listing available topics, or handling advanced troubleshooting, but agents can likely work around these with the provided tools for most common tasks.