MCPHOST-SERVER

What is MCPHOST-SERVER?

MCPHOST-SERVER is a server bridging solution for MCPHOST that enables easy communication with a local LLM (Ollama) through HTTP requests. It is a fork of mark3labs/mcphost that adds server capabilities for enhanced functionality.

How to use MCPHOST-SERVER?

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.

Key features of MCPHOST-SERVER

• 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

Use cases of MCPHOST-SERVER

• Exposing local Ollama LLM capabilities through HTTP endpoints
• Integrating MCPHOST with external applications via REST API
• Running LLM interactions in a server context without a CLI
• Testing or prototyping MCP tools with a local LLM backend

FAQ from MCPHOST-SERVER

How do I start the MCPHOST-SERVER?

Run ./mcphost-server after building the project. The server will start in server mode on the configured port.

How do I change the port or other settings?

Edit the .env file (copy from .example.env) or use command-line flags. The default port is 8115.

Can I use the command-line interface instead of the server?

Yes. Set server_mode = false in main.go, rebuild the project, and then run ./mcphost-server to use CLI mode.

What LLM does MCPHOST-SERVER work with?

It is designed to work with a local LLM via Ollama.

How do I configure MCPHOST-SERVER?

Use environment variables (via .env file), a mcp.json configuration file, or command-line flags. See .example.env for details.