Browse MCP servers — page 104

MCP server for safer coding agents with skill routing, C4 workflow gates, memory checks, and verification.

Langfuse MCP 服务器，用于通过自然语言访问和分析遥测数据。需要提供 Langfuse 凭据（公共密钥、私密密钥、主机 URL），可以通过环境变量 LANGFUSE_PUBLIC_KEY、LANGFUSE_SECRET_KEY 和 LANGFUSE_HOST 设置。

An open-source MCP server that connects Clio document management with Claude Desktop. Requires environment variables for Clio API credentials configured via .env or Claude Desktop config.

A Node.js server implementing Model Context Protocol (MCP) for media processing operations, providing powerful video and image manipulation capabilities. Requires external system dependencies FFmpeg and ImageMagick for video and image processing respectively.

A Model Context Protocol (MCP) server that provides SSH access to remote servers, allowing AI tools like Claude Desktop or VS Code to securely connect to your VPS for website management.

用于预览本地 HTML 文件和捕获截图的 MCP 服务器。截图会保存到项目文件夹中的本地 'screenshots/' 目录中。

AI-Powered MCP Gateway for Tool Orchestration. Configured via environment variables (e.g., OPENAI_API_KEY, LOG_LEVEL, FRONTEND_PORT) and initializationOptions for backend MCP servers.

用于 Awesome-llms-txt 的 MCP 服务器。通过 MCP 资源将文档直接添加到您的对话中。无需外部数据文件。

一个自定义的模型上下文协议（MCP）服务器实现，提供文件系统和命令执行工具，适用于Claude桌面和其他大型语言模型（LLM）客户端。

一个 Model Context Protocol (MCP) 服务器，连接 AI 助手（如 Claude）与 Moneybird 会计软件，通过 API 进行通信。需要一个包含 MONEYBIRD_API_TOKEN 和 MONEYBIRD_ADMINISTRATION_ID 环境变量的 .env 文件，用于身份验证。

Papez is a scoring engine, causal graph, and lifecycle manager for AI memory. It provides an in-memory causal graph engine with optional JSON persistence and a stdio MCP server. No database dependency or REST API is included. The package can be installed via pip and run as a stdio MCP server.

PortOne MCP Server is a Model Context Protocol server for PortOne users. It provides official documentation content from PortOne Developer Center and Help Center to LLMs for accurate user integration and queries. Requires external documentation repositories 'developers.portone.io' and 'help.portone.io' to be cloned locally and their paths configured via environment variables DEVELOPERS_PORTONE_IO_PATH and HELP_PORTONE_IO_PATH for updating docs.