MCP-smallest-ai
MCP-smallest-ai
claude mcp add --transport stdio vinayaktiwari1103-mcp-smallest-ai node index.ts \ --env BASE_URL="https://atoms-api.smallest.ai/api/v1" \ --env SMALLEST_AI_API_KEY="your_api_key_here"
How to use
MCP-Smallest.ai provides a standardized interface to interact with Smallest.ai's knowledge base management features through the Model Context Protocol. It exposes tools to list, create, and retrieve knowledge bases, acting as middleware between client applications and the Smallest.ai API. Clients connect to the MCP server using the MCP protocol, share requests, and receive uniformly structured responses. The server handles authentication, parameter validation, error handling, and formatting of results for downstream consumption.
To use the server, start it with the supported runtime (the project is configured to run with Bun/Node). Once running, you can call the available tools via the MCP protocol. The documented tools include listKnowledgeBases, createKnowledgeBase, and getKnowledgeBase. Each tool accepts a specific set of arguments and returns a standardized response structure containing the relevant knowledge base data or confirmation of the performed action. This setup simplifies integration by providing a consistent interface regardless of the underlying Smallest.ai API intricacies.
How to install
Prerequisites:
- Node.js 18+ or Bun runtime
- Access to Smallest.ai API key
- TypeScript knowledge (for development and configuration)
Installation steps:
-
Clone the repository git clone https://github.com/yourusername/MCP-smallest.ai.git cd MCP-smallest.ai
-
Install dependencies (choose one):
- If using Bun: bun install
- If using npm/yarn (less common for this project): npm install
-
Create a .env file in the project root with your API key: SMALLEST_AI_API_KEY=your_api_key_here
-
Configure the API details (example config.ts): export const config = { API_KEY: process.env.SMALLEST_AI_API_KEY, BASE_URL: 'https://atoms-api.smallest.ai/api/v1' };
-
Start the server (examples):
- Using Bun: bun run index.ts
- Using Node (if transpiled/compiled appropriately): node index.js
-
Verify the server is running and listening on the configured port (default logs will indicate the listening address).
Additional notes
Environment variables and configuration:
- SMALLEST_AI_API_KEY is required for authentication with Smallest.ai.
- BASE_URL should point to the Smallest.ai API base endpoint.
Common issues:
- Missing or invalid API key leads to authentication errors from Smallest.ai.
- Ensure the runtime (Node 18+ or Bun) is installed and properly set up.
- If using TypeScript source directly, ensure the server entrypoint (index.ts) is compatible with the runtime (bun run works with Bun; node may require transpilation to JavaScript).
Configuration tips:
- Keep your API key secure and do not commit it to version control.
- You can extend the config.ts to include additional middleware or logging as needed.
Related MCP Servers
mcp-router
A Unified MCP Server Management App (MCP Manager).
agent
A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.
pluggedin-app
The Crossroads for AI Data Exchanges. A unified, self-hostable web interface for discovering, configuring, and managing Model Context Protocol (MCP) servers—bringing together AI tools, workspaces, prompts, and logs from multiple MCP sources (Claude, Cursor, etc.) under one roof.
postman
A Model Context Protocol (MCP) server that provides seamless integration with the Postman API. This package enables AI assistants and applications to interact with Postman workspaces, collections, requests, environments, and folders programmatically.
npm-sentinel
A powerful Model Context Protocol (MCP) server that revolutionizes NPM package analysis through AI.
mcp-bundler
Is the MCP configuration too complicated? You can easily share your own simplified setup!