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.
@JinsonWu
基本信息
MCP server for ollama, openai, and anthropic bridging
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
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.
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.
.env filemcp.json configuration fileRun `./mcphost-server` after building the project. The server will start in server mode on the configured port.
Edit the `.env` file (copy from `.example.env`) or use command-line flags. The default port is 8115.
Yes. Set `server_mode = false` in `main.go`, rebuild the project, and then run `./mcphost-server` to use CLI mode.
It is designed to work with a local LLM via Ollama.
Use environment variables (via `.env` file), a `mcp.json` configuration file, or command-line flags. See `.example.env` for details.
28-tool MCP server for web scraping, crawling, deep research & autonomous extraction — clean Markdown & structured JSON for Claude, Cursor & any MCP client. 1,000 free one-time credits, local-Ollama LLM support.

Give an agent access to your YouSpot CRM: contacts, companies, notes, files, and your connected Gmail, Calendar, HubSpot, LinkedIn, Slack and X.
Official MCP server for BlazingCDN - AI agents (Claude, Cursor, Windsurf) manage CDN resources, purge cache, query metrics, domains, Anycast CDN, Video CDN and Media CDN
HeyLead: AI agent for LinkedIn outreach. Finds the right people, writes in your voice, follows up and handles replies, from Claude Code, Cursor, any MCP client or a web dashboard.
MCP-native LLM councils for debates, juries, blind panels, voting, refinement, and custom multi-model deliberation.
评论