mcpField
M
MCPHOST-SERVER

MCPHOST-SERVER

Local
github.com/JinsonWuAI & Agents2Updated 73w ago
Repository

About MCPHOST-SERVER

MCPHOST-SERVER adds an HTTP server mode to MCPHOST for interactive requests to a local LLM, including Ollama. It is intended for applications that need HTTP access, with configuration through environment variables, a file, or command-line flags.

Key features

  1. 01HTTP server mode for interactive requests
  2. 02Connect to a local LLM such as Ollama
  3. 03Configure through environment variables
  4. 04Read mcp.json and command-line flags

Use cases

  1. 01Send interactive requests to a local LLM over HTTP
  2. 02Configure server settings through environment variables

MCP support

The project is an MCP server bridging solution. Its README describes HTTP access to a local LLM but does not specify which MCP tools or resources it exposes.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

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

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.