About JigsawStack MCP Server
JigsawStack MCP Server is a set of MCP servers that let AI models call JigsawStack models. Built with Node.js and Express.js, each tool sits in its own directory so tools can be added, removed or updated independently.
Key features
- 01Built with Node.js and Express.js
- 02Each tool isolated in its own directory
- 03Authentication via JIGSAWSTACK_API_KEY environment variable
- 04Includes web scraping, AI search and image generation tools
Use cases
- 01Letting an LLM scrape web content
- 02Running AI-powered search for complex queries
- 03Generating images from prompts as base64 strings
MCP support
The project is an MCP server that exposes JigsawStack-backed tools, such as web scraping, search and image generation, to LLMs.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEJigsawStack MCP Server
Introduction
JigsawStack MCP (Model Context Protocol) Server is a versatile platform designed to facilitate the integration and management of various tools. Each directory within the server represents a distinct tool that can be utilized for different purposes by an LLM. The server is built using Node.js and Express.js, and each tool is encapsulated within its own directory, making it easy to add, remove, or update tools without affecting the overall system.
Start by obtaining your JIGSAWSTACK_API_KEY from the our website. You will need this key to access the JigsawStack services. You can get your API key by signing up for a free account at JigsawStack.
You can also install our MCPs via Smithery AI
Installation
Prerequisites
- Ensure you have
gitinstalled on your system. - Ensure you have
node.jsandnpminstalled. - Alternatively, you can use
yarninstead ofnpm. as a package manager.
Steps to Setup the repository:
- Clone the repository:
git clone https://github.com/yourusername/jigsawstack-mcp-server.git - Navigate to the project directory:
cd jigsawstack-mcp-server - Install the necessary dependencies:
npm install or yarn install
What is MCP?
MCP stands for Model Context Protocol. It is a framework that allows users to integrate LLMs and manage various tools and components exposing external data in a modular fashion. Here each tool is encapsulated within its own directory, making it easy to add, remove, or update tools without affecting the overall system.
Using JigsawStack MCP Server
There are four tools available in the MCP Server. Each tool is contained within its own directory and has its own set of instructions for use.
Running a tool
To run a tool,
- cd into the tool directory and follow the instructions.
- Export the JIGSAWSTACK_API_KEY environment variable with your JIGSAWSTACK API key.
export JIGSAWSTACK_API_KEY=your_api_key - Start the server:
npm start - Access the server through your web browser at
http://localhost:3000.
Directory Structure
/ai-web-scraper: Let AI scrape the internet for you!/ai-web-search: Search powered by AI capable of handling complex queries./image-generation: Generate images using prompts, to receive a base64 string of the image.
Contact
For any questions or issues, please contact us at [email protected].
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.