MCP ExplorerExplorer

Kevo Mcp

@KevoDBon a month ago
1 MIT
FreeCommunity
AI Systems
An MCP server for accessing your data on Kevo

Overview

What is Kevo Mcp

Kevo-MCP is a server that implements the Multimodal Communication Protocol (MCP) for accessing and interacting with KevoDB, allowing AI agents to utilize a standardized API for data operations.

Use cases

Use cases for Kevo-MCP include AI-driven applications that need to retrieve, store, or manipulate data in KevoDB, such as chatbots accessing user data, automated reporting tools, and systems requiring batch processing of database transactions.

How to use

To use Kevo-MCP, first install the required dependencies using pip. Ensure that KevoDB is running, then start the MCP server by executing ‘python main.py’. Configure the KevoDB connection with environment variables if needed. AI agents can connect to the server and use various tools for data operations.

Key features

Key features of Kevo-MCP include: exposing KevoDB operations through MCP tools, supporting core functionalities like basic key-value operations, range scans, transactions, batch operations, and providing database statistics. It uses a simple string-based API with UTF-8 encoding.

Where to use

Kevo-MCP can be used in fields that require data management and interaction through AI agents, such as data analytics, machine learning applications, and any system that benefits from a structured database interface.

Content

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

Prerequisites

  • Python 3.8+
  • Running KevoDB server (default: localhost:50051)
  • FastMCP library
  • Python-Kevo SDK

Installation

  1. Install dependencies:
pip install fastmcp python-kevo
  1. Ensure KevoDB is running on localhost:50051 (or set the KEVO_HOST and KEVO_PORT environment variables to connect to a different endpoint)

Usage

Running the MCP Server

Start the MCP server:

python main.py

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:

KEVO_HOST=192.168.1.100 KEVO_PORT=5000 python main.py

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 Connect to the KevoDB server
get Get a value by key from KevoDB
put Store a key-value pair in KevoDB
delete Delete a key-value pair from KevoDB
scan Scan keys in KevoDB with options
batch_write Perform multiple operations in a batch
get_stats Get database statistics
begin_transaction Begin a new transaction and return transaction ID
commit_transaction Commit a transaction by ID
rollback_transaction Roll back a transaction by ID
tx_put Store a key-value pair within a transaction
tx_get Get a value by key within a transaction
tx_delete Delete a key-value pair within a transaction
cleanup Close the KevoDB connection

Integration with AI Applications

To use KevoDB with your AI application:

  1. Start the KevoDB server
  2. Start this MCP server
  3. Configure your AI agent to connect to the MCP endpoint
  4. The AI agent can now use all KevoDB operations through the MCP interface

License

MIT

Tools

No tools

Comments

Recommend MCP Servers

View All MCP Servers