MCPHOST-SERVER

by JinsonWu

2 stars
127 downloads
Not rated
GitHub

About

MCP server for ollama, openai, and anthropic bridging

Details

Author
JinsonWu
GitHub stars
2
Downloads
127
Categories
AI

- HTTP-based server mode for interactive LLM requests
- Environment-based configuration via .env file
- Support for mcp.json configuration file
- Command-line flags for configuration
- Default listen port 8115

Clone the repository, copy .example.env to .env and configure it, then build with go build and run with ./mcphost-server. The server starts on the configured port (default 8115) in server mode by default. To use the command-line interface, set server_mode = false in main.go and rebuild.

MCPHOST-SERVER

A server bridging solution for MCPHOST that enables easy communication with local LLM (Ollama) through HTTP requests. This project is originated from mark3labs/mcphost and adds server capabilities for enhanced functionality.

Added Features

- Server mode for HTTP-based communication with local LLM for interactive requests
- Environment-based configuration

Getting Started

1. Clone the repository

2. Copy the example environment file and configure it, see .env for configuration in details:

   cp .example.env .env

3. Build the project:

   go build

4. Run the server:

   ./mcphost-server

Usage

Server Mode

The server mode is enabled by default and provides HTTP endpoints for interacting with the local LLM. The server will start on the configured port (default: 8115).

Command Line Mode

To use the command-line interface, set server_mode = false in the main.go file and rebuild the project.

Configuration

The application can be configured through:
- Environment variables (see .example.env)
- mcp.json configuration file
- Command-line flags

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.