Provides an interface for AI agents to interact with KevoDB, a key-value database, enabling operations like basic key-value operations, range/prefix/suffix scans, transactions, batch operations, and database statistics retrieval.
KevoDB MCP Server
This project implements a MCP (Multimodal Communication Protocol) server for KevoDB, allowing AI agents to interact with KevoDB using a standardized API.
Features
Exposes KevoDB operations through MCP tools
Supports all core KevoDB functionality:
Basic key-value operations (get, put, delete)
Range, prefix, and suffix scans
Transactions
Batch operations
Database statistics
Simple string-based API with UTF-8 encoding
Related MCP server: Kubectl MCP Tool
Prerequisites
Python 3.8+
Running KevoDB server (default: localhost:50051)
FastMCP library
Python-Kevo SDK
Installation
Install dependencies:
Ensure KevoDB is running on localhost:50051 (or set the
KEVO_HOSTandKEVO_PORTenvironment variables to connect to a different endpoint)
Usage
Running the MCP Server
Start the MCP server:
This will launch the MCP server on http://localhost:9000/mcp
You can configure the KevoDB connection using environment variables:
KEVO_HOST: Hostname of the KevoDB server (default: "localhost")KEVO_PORT: Port of the KevoDB server (default: "50051")
Example:
Using with AI Agents
AI agents that support MCP can connect to this server and use all exposed tools. The server provides the following tools:
Tool | Description |
| Connect to the KevoDB server |
| Get a value by key from KevoDB |
| Store a key-value pair in KevoDB |
| Delete a key-value pair from KevoDB |
| Scan keys in KevoDB with options |
| Perform multiple operations in a batch |
| Get database statistics |
| Begin a new transaction and return transaction ID |
| Commit a transaction by ID |
| Roll back a transaction by ID |
| Store a key-value pair within a transaction |
| Get a value by key within a transaction |
| Delete a key-value pair within a transaction |
| Close the KevoDB connection |
Integration with AI Applications
To use KevoDB with your AI application:
Start the KevoDB server
Start this MCP server
Configure your AI agent to connect to the MCP endpoint
The AI agent can now use all KevoDB operations through the MCP interface