Context Bank MCP
An MCP server that provides an interface for querying the AtherOS knowledge base through an API, allowing users to create chat sessions and send queries to retrieve information.
README
Context Bank MCP
Overview
Context Bank MCP is a project using the Model Context Protocol (MCP) to create an interface for querying the AtherOS knowledge base through an API. This project builds an MCP server capable of interacting with the Onyx API to create chat sessions and send queries to the knowledge base.
Features
- Create new chat sessions to query the knowledge base
- Send messages to chat sessions to receive responses from the knowledge base
- Format and display results from the Onyx API
Technologies Used
- TypeScript
- Node.js
- Model Context Protocol (MCP) SDK
- Zod for data validation
- Axios for HTTP requests
Installation
# Install dependencies
npm install
# Compile source code
npm run build
Configuration
The project uses environment variables to connect to the Onyx API. Follow these steps to configure your environment:
Automatic Setup (Recommended)
Run the setup script to configure your environment interactively:
npm run setup
This script will:
- Create a
.envfile if it doesn't exist - Prompt you for your AtherOS API key
- Allow you to customize the API base URL
- Set default values for other configuration options
Manual Setup
- Copy the example environment file to create your own:
cp .env.example .env
- Edit the
.envfile with your specific configuration:
# AtherOS API Configuration
ONYX_API_KEY=your_api_key_here
ONYX_API_BASE=http://your_api_base_url:port
# Server Configuration
PORT=3000
NODE_ENV=development
# Optional: Logging Configuration
LOG_LEVEL=info
Environment Variables
-
Required Environment Variables:
ONYX_API_KEY: Your AtherOS API keyONYX_API_BASE: Base URL for the AtherOS API (e.g., "http://172.30.22.52:3000")
-
Optional Environment Variables:
PORT: Port number for the server (default: 3000)NODE_ENV: Environment mode (development, production, test)LOG_LEVEL: Logging level (info, debug, error, warn)
Usage
After compilation, you can use the command line tool:
# Direct usage
./build/index.js
# Or through npm
npm start
API Tools
The project provides two main MCP tools:
1. create_chat_session
Creates a new chat session to query the knowledge base.
Parameters:
persona_id(default: 0): User IDdescription(default: ""): Chat session description
2. query_atheros
Sends a message to the chat session to query the AtherOS knowledge base.
Parameters:
chat_session_id: Chat session IDmessage: Message contentparent_message_id: Parent message ID (can be null)
Response Format
Responses from knowledge base queries include:
- Message ID
- Message content
- Rephrased query (if available)
- Information about top source documents (if available):
- Document name
- Relevance score
- Link to the document
Architecture
The project is organized with a simple structure:
src/index.ts: Main entry point of the application, defines the MCP tools and connection logic- Uses the stdio protocol to communicate with the MCP server
Development
# Compile and view changes
npm run build
# Run in development mode
npm run dev
License
ISC
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.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.