interactive-mcp
by ttommyth · ai-ml · mcp-server, lobehub, validated, tools
A MCP Server implemented in Node.js/TypeScript, facilitating interactive communication between LLMs and users. Designed to run locally alongside the MCP client to access the user's OS for notifications and command-line prompts.
Source: https://github.com/ttommyth/interactive-mcp
Install
git clone https://github.com/ttommyth/interactive-mcpUse this forAI-extracted
- →Create human-in-the-loop checkpoints where AI agents pause for user confirmation before executing code changes
- →Enable interactive debugging sessions where developers can inspect and modify AI agent decisions in real-time
- →Build safety guardrails for autonomous AI coding by requiring human approval on risky operations
- →Facilitate collaborative AI-assisted development with bidirectional communication between agent and developer
Works with
Tags: mcp-server, lobehub, validated, tools
⭐ 76 GitHub stars · Source: lobehub
About ai-ml MCP servers and Claude skills
ai-ml MCP servers extend what AI agents can do inside Claude Code, Cursor, Copilot, Codex, and Windsurf. The Skiln directory indexes 16,000+ such integrations across 22 categories.
interactive-mcp is one of hundreds of ai-ml entries indexed on Skiln. Browse the full ai-ml category or the complete directory of Claude skills, MCP servers, agents, commands, and hooks.
Related ai-ml MCPs and skills
- JiraMCP by goroskob
一个 Model Context Protocol (MCP) 服务器，封装了 jira-cli，以将 Jira 功能暴露给大型语言模型。需要在 .env 文件中配置 Jira 凭据的环境变量（例如 JIRA_API_TOKEN、JIRA_SERVER、JIRA_LOGIN）。
- Alpaca MCP Server by alpacahq
用于 Alpaca 交易 API 的模型上下文协议（Model Context Protocol）服务器，支持大型语言模型（LLMs）与 Alpaca 的股票、期权、投资组合、观察列表和实时市场数据基础设施交互。需要通过环境变量（ALPACA_API_KEY、ALPACA_SECRET_KEY）配置的外部 API 密钥，通常在 .env 文件中设置。
- zscaler-aiguard-control-plane-mcp by hshen-ai
Provides AI agents with programmatic access to Zscaler AI Guard, enabling autonomous management of detection policies, match rules, LLM applications, and LLM providers.
- grafana-mcp-observability by akkireddy-challa
Enables AI agents to query Grafana dashboards, alerts, and datasources for observability insights and incident investigation.
- Switchback MCP by VibeKit-Bot
Classifies AI agent turns by complexity and recommends the cheapest model that can handle them, reducing costs in multi-step workflows.
- HL7-Bridge MCP by GlennRTC
Translates HL7 v2.x messages to FHIR R4, validates against profiles like US Core, and explains errors in natural language for AI agents.
- yandex-messenger-mcp by conarti
MCP server for Yandex Messenger that enables reading chats, searching, downloading attachments, and sending messages via agent, using a web session with Playwright and a reverse-engineered protocol.
- gmapsscraper by gmapsscraper
Enables AI assistants to scrape Google Maps business data (names, addresses, phones, emails, websites, ratings, etc.) through natural language queries, with tools for synchronous and asynchronous scraping and credit checking.
Frequently asked questions
How do I install interactive-mcp?
Add the install command above to your Claude Code, Cursor, or Windsurf MCP configuration. Most servers register via npx, a local command, or a Docker image. Refer to the source repository for environment variables and credential requirements.
Which clients support interactive-mcp?
Any MCP-compatible client works: Claude Desktop, Claude Code CLI, Cursor, Windsurf, Zed, and VS Code with the official MCP extension. OpenAI Codex and GitHub Copilot increasingly support MCP via adapter bridges.
Is interactive-mcp free?
The server itself is typically open source. Any upstream service (API keys, paid tiers, hosted infrastructure) may have its own pricing. Check the source repository for details.