#mcp-server

A Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.

Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors

Official MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.

A Serper MCP Server

An MCP server implementation for retrieving information from the AWS Knowledge Base using the Bedrock Agent Runtime.

Model Context Protocol server that integrates AgentQL's data extraction capabilities.

Official Firecrawl MCP Server - Adds powerful web scraping to Cursor, Claude and any other LLM clients.

Write notes to Flomo

summarize chat message

Flag features directly from chat in your code editor, including VS Code, Cursor, Windsurf, Claude Code—any IDE with MCP support.

MCP Server that gives AI coding assistants instant access to your entire codebase through a persistent Tree-sitter index. Instead of grep flooding your context with 2000+ tokens per search, AiDex returns precise identifier matches in ~50 tokens. Supports 11 languages: C#, TypeScript, JavaScript, Rust, Python, C, C++, Java, Go, PHP, Ruby. Features include method signatures, cross-project search, time-based filtering, session notes, and an interactive browser-based viewer.

RLM solves Claude Code's biggest limitation: memory loss. Every time you /compact or hit the context limit, your decisions, insights, and conversation history disappear. RLM fixes this with an MCP server that auto-saves before context loss, lets you store key decisions as searchable insights, and keeps your full conversation history in persistent chunks. Features include BM25 ranked search, fuzzy matching (typo-tolerant), multi-project organization, and smart retention that auto-archives old chunks. Inspired by MIT CSAIL's Recursive Language Models paper. Install in 3 lines, zero configuration needed.

An enterprise-grade Oracle Database connector for MCP. Features built-in self-healing connection retries, TypeScript-based architecture, and AI-guided SQL error handling for autonomous agent workflows.

CodeSherlock is an AI- based code analysis tool that validates unstaged changes and commits directly inside IDEs and AI Agents. It helps developers catch security, quality, and design issues early by combining deep analysis with compliance-aware checks OWASP, CWE, SOC-2 at the moment code is written. CodeSherlock also performs other security vulnerability reviews along with Maintainability, Reliability and Scalability checks. Use CodeSherlock to review and validate code especially generated via AI.

AI/ML-powered diagnostic engine for SRE Observability on Konflux and OpenShift. It uses the Model Context Protocol (MCP) and 40+ tools to analyze logs, metrics, and traces, enabling automated RCA and predictive analysis.

High-performance MCP server for USPTO Patent File Wrapper API with secure document downloads, metadata access, and context reduction

High-performance MCP server for USPTO Patent Trial and Appeal Board (PTAB) with context reduction, progressive disclosure workflows, and seamless cross-MCP integration

Official Rebrandly MCP Server Rebrandly offers an official MCP server that connects AI assistants like Claude, Gemini, and GitHub Copilot to your Rebrandly account with full-featured support for: Link Management - Create, update, search, and organize branded short links Analytics - Access click statistics, geographic data, and device information Account Management - Workspace administration, teammate management, and domain operations

The Jotform MCP server provides programmatic access to forms and submissions via natural language interfaces, compatible with popular AI assistants including Cursor and VS Code extensions. Implementation follows the open Model Context Protocol specification, ensuring interoperability with any MCP-compatible client. The service is actively being optimized based on real-world usage patterns.This MCP is actively maintained and more tools will come soon.

A production-ready MCP server that gives AI agents deep codebase understanding. Features AST-based semantic analysis, context-aware security scanning (zero false positives on source code), safe refactoring tools with previews, and comprehensive Git operations.

Manage, explore, transform and join data in Kafka topics across multiple clusters using different flavours of Apache Kafka via Lenses.io (including the free Community Edition)

Turn Claude or Cursor into your personal AI Financial Analyst. FinancialData.Net API provides end-of-day and intraday stock market data, company financial statements, key financial ratios and metrics, insider and institutional trading data, sustainability data, earnings releases, and much more. Over 20 years of historical data is available, including information on 17,000+ stocks, 20,000+ funds, 3,000+ ETFs, 13,000+ OTC securities, and 200,000+ derivatives.

Manage, explore, transform and join data in Kafka topics across multiple clusters using different flavours of Apache Kafka via Lenses.io (including the free Community Edition)

Project description 🧠 RABEL MCP Server Recidive Active Brain Environment Layer Local-first AI memory with semantic search, graph relations, and soft pipelines. Mem0 inspired, HumoticaOS evolved. By Jasper & Root AI from HumoticaOS 💙 🚀 Quick Start # Install pip install mcp-server-rabel # For full features (vector search) pip install mcp-server-rabel[full] # Add to Claude CLI claude mcp add rabel -- python -m mcp_server_rabel # Verify claude mcp list # rabel: ✓ Connected 🤔 What is RABEL? RABEL gives AI assistants persistent memory that works 100% locally. Before RABEL: AI: "Who is Storm?" → "I don't know, you haven't told me" After RABEL: You: "Remember: Storm is Jasper's 7-year-old son" AI: *saves to RABEL* Later... You: "Who is Storm?" AI: *searches RABEL* → "Storm is Jasper's 7-year-old son!" No cloud. No API keys. No data leaving your machine. 🛠️ Available Tools Tool Description rabel_hello Test if RABEL is working rabel_add_memory Add a memory (fact, experience, knowledge) rabel_search Semantic search through memories rabel_add_relation Add graph relation (A --rel--> B) rabel_get_relations Query the knowledge graph rabel_get_guidance Get soft pipeline hints (EN/NL) rabel_next_step What should I do next? rabel_stats Memory statistics 📖 Examples Adding Memories # Remember facts rabel_add_memory(content="Jasper is the founder of HumoticaOS", scope="user") rabel_add_memory(content="TIBET handles trust and provenance", scope="team") rabel_add_memory(content="Always validate input before processing", scope="agent") Searching Memories # Semantic search - ask questions naturally rabel_search(query="Who founded HumoticaOS?") # → Returns: "Jasper is the founder of HumoticaOS" rabel_search(query="What handles trust?") # → Returns: "TIBET handles trust and provenance" Knowledge Graph # Add relations rabel_add_relation(subject="Jasper", predicate="father_of", object="Storm") rabel_add_relation(subject="TIBET", predicate="part_of", object="HumoticaOS") rabel_add_relation(subject="RABEL", predicate="part_of", object="HumoticaOS") # Query relations rabel_get_relations(subject="Jasper") # → Jasper --father_of--> Storm rabel_get_relations(predicate="part_of") # → TIBET --part_of--> HumoticaOS # → RABEL --part_of--> HumoticaOS Soft Pipelines (Bilingual!) # Get guidance in English rabel_get_guidance(intent="solve_puzzle", lang="en") # → "Puzzle: Read → Analyze → Attempt → Verify → Document" # Get guidance in Dutch rabel_get_guidance(intent="solve_puzzle", lang="nl") # → "Puzzel: Lezen → Analyseren → Proberen → Verifiëren → Documenteren" # What's next? rabel_next_step(intent="solve_puzzle", completed=["read", "analyze"]) # → Suggested next step: "attempt" 🏗️ Architecture ┌─────────────────────────────────────────────────────────────┐ │ RABEL │ │ Recidive Active Brain Environment Layer │ ├─────────────────────────────────────────────────────────────┤ │ │ │ Memory Layer → Semantic facts with embeddings │ │ Graph Layer → Relations between entities │ │ Soft Pipelines → Guidance without enforcement (EN/NL) │ │ │ │ Storage: SQLite + sqlite-vec (optional) │ │ Embeddings: Ollama nomic-embed-text (optional) │ │ │ │ 100% LOCAL - Zero cloud dependencies │ │ │ └─────────────────────────────────────────────────────────────┘ Graceful Degradation RABEL works with minimal dependencies: Feature Without extras With [full] Text memories ✅ ✅ Text search ✅ (LIKE query) ✅ (semantic) Graph relations ✅ ✅ Soft pipelines ✅ ✅ Vector search ❌ ✅ Embeddings ❌ ✅ (Ollama) 🌍 Philosophy "LOKAAL EERST - het systeem MOET werken zonder internet" (LOCAL FIRST - the system MUST work without internet) RABEL is built on the belief that: Your data stays yours - No cloud, no tracking, no API keys Soft guidance beats hard rules - Pipelines suggest, not enforce Bilingual by default - Dutch & English, more coming Graceful degradation - Works with minimal deps, better with more 🙏 Credits Inspired by: Mem0 - Thank you for the architecture insights! We took their ideas and made them: 100% local-first Bilingual (EN/NL) With soft pipelines With graph relations 🏢 Part of HumoticaOS RABEL is part of a larger ecosystem: Package Purpose Status mcp-server-tibet Trust & Provenance ✅ Available mcp-server-rabel Memory & Knowledge ✅ Available mcp-server-betti Complexity Management 🔜 Coming 📞 Contact HumoticaOS Website: humotica.com GitHub: github.com/jaspertvdm 📜 License MIT License - One love, one fAmIly 💙 Built with love in Den Dolder, Netherlands By Jasper & Root AI - December 2025

A file mover tool that stages and executes file moves safely. Works as both a CLI tool and an MCP server for AI agents. - Session-based workflow: Stage multiple file moves, preview them, then commit all at once - Safety first: Preview changes before executing, validate file paths and conflicts - Dual mode: Works as both a command-line tool (fm) and an MCP server for AI agents - Overwrite control: Explicit opt-in for overwriting existing files - Clear error messages: Actionable guidance when things go wrong

Imdb146 MCP 服务器可帮助您轻松获取电影、视频及相关信息。

MCP Go Server connects AI assistants like Claude directly to the Go runtime. It acts as a bridge, giving your AI the necessary tools to execute, manage, and optimize Go-based development workflows efficiently.

An MCP server for executing token swaps across multiple decentralized exchanges using OpenOcean's aggregation API.

一个轻量级的主机信息获取MCP工具，通过MCP（模型上下文协议）接口提供系统信息，基于Spring Boot3+Spring AI+OSHI（操作系统和硬件信息）库构建。

Git-driven MCP Server for managing Prompt templates with Handlebars support. Store prompts in Git, sync automatically, and use dynamic templates in Cursor, Claude Desktop, and other MCP clients. Features hot-reload, group filtering, version management, and Docker/Kubernetes deployment support.

Markdown-First MCP Server for Notion - Composite Actions, Auto-Pagination, Bulk Operations optimized for AI Agents

MCP Server for Mailjet SaaS Platform

A Model Context Protocol (MCP) server that provides secure SSH capabilities for AI assistants, enabling remote command execution, SFTP file transfers, and port forwarding with comprehensive security controls. Features: - 🔐 Secure SSH Command Execution - Execute commands on remote servers with granular security controls - 🛡️ Host Allowlisting - Only connect to pre-configured, trusted servers - 📁 SFTP File Operations - Upload, download, list, and delete files on remote servers - 🌉 SSH Port Forwarding - Create secure tunnels to access remote services - 🔄 Connection Pooling - Persistent connections with automatic management - 🔑 SSH Key Authentication - Secure authentication using SSH private keys - ⚙️ SSH Config Integration - Import servers from your existing SSJ config file - ✅ Command Allowlisting - Restrict which commands can be executed - 📦 Named Services - Pre-configured port forwarding services for common use cases - 🎯 Command Templates - Reusable parameterized commands with variable substitution

MCP server allows agents to break tasks down and execute them sequentially.

This is an MCP (Model Context Protocol) server for integrating with Lumin's API services. It allows AI assistants (MCP clients, e.g Claude Desktop, Cursor) to interact with Lumin features such as document management, signature requests, and user information.

A Model Context Protocol (MCP) server that enables AI applications to search for YouTube music videos and manage playlists using the official YouTube Data API v3.

A Model Context Protocol (MCP) server that enables AI assistants to interact with Power BI workspaces, datasets, reports, and dashboards programmatically. 🚀 Features Workspace Management: List and manage Power BI workspaces Report Operations: Access, clone, export, and rebind reports Dataset Management: Execute DAX queries, refresh datasets, manage schedules Dashboard Access: List and interact with dashboards Push Datasets: Create and manage push datasets with real-time data Authentication: Secure OAuth2 authentication with Microsoft Entra ID 📋 Prerequisites Node.js (v18 or higher) npm or yarn Power BI Pro or Premium license Microsoft Entra ID app registration MCP-compatible AI assistant (Claude Desktop, etc.)

Enterprise-Grade HR Assistant leveraging Model Context Protocol for seamless employee data and HR policy queries

一个强大的 MCP (Model Context Protocol) 服务器，用于智能读取 Java 源代码。支持从 Maven 依赖和本地项目中提取源码，配备双反编译器（CFR/Fernflower）自动选择机制，智能处理 SNAPSHOT 版本，完美支持多模块项目，让 AI 助手能够深入理解你的 Java 代码库。

An MCP (Model Context Protocol) server that enables LLMs to interact with Cisco Intersight APIs. This server exposes Intersight operations as tools for LLM applications. The Intersight MCP Server includes an intelligent Security & Health Check Agent that automatically orchestrates comprehensive infrastructure analysis when security or health checks are requested.

Persistent codebase intelligence that gives agents memory across sessions.

The Sonatype MCP Server enables AI assistants to access Sonatype's comprehensive dependency intelligence directly within your development workflow. By integrating with the Model Context Protocol, your AI assistant can help you make informed decisions about dependencies, identify security risks, and maintain compliance — all without leaving your IDE. Key Features Component Version Selection - Select the best version the first time, without the side quest Security Vulnerability Scanning - Identify known vulnerabilities in your project dependencies License Compliance Checking - Ensure your dependencies meet your organization's license policies Dependency Health Analysis - Get insights into dependency quality, maintenance status, and risk factors Real-time Security Advisories - Stay informed about the latest security threats affecting your dependencies Remediation Guidance - Receive actionable recommendations to fix vulnerabilities and compliance issues

优惠券自动获取一键采集，吃喝玩乐、美团饿了么、0元试吃券、打车优惠、机票火车票优惠券活动、一键采集，自动获取常用的优惠列表以及小程序二维码优惠券领取连接

An MCP server for accessing TopicLake policy insights data, including documents, topics, Q&A, sentiment, and summaries, using the Stainless SDK. Easily integrates with Claude Desktop, Abacus.AI DeepAgent, and other MCP-compatible tools.

Discover the power of the “CLGateway”, an the open-source Claude MCP Server Gateway (available on GitHub). Built for users of Claude Desktop, Claude API or Claude Code, this Python-based gateway smartly manages your MCP (Model Context Protocol) servers and dramatically slashes token usage, cutting MCP context bloat by roughly 95%. Rather than forcing Claude to load every tool from all configured MCP servers (often thousands of tokens wasted upfront), the gateway exposes just three core tools initially. When you need a specific MCP server (GitHub, Google Workspace, DataForSEO, etc.), the gateway dynamically loads only what’s required, reducing tokens used, improving context clarity, and boosting performance.

A comprehensive MCP server for processing, validating, optimizing, and analyzing 3D models with glTF/GLB support.

MCP server that enables LLM clients to interact with macOS applications through AppleScript. Built using the @beyondbetter/bb-mcp-server library, this server provides safe, controlled execution of predefined scripts with optional support for arbitrary script execution.

RUN ALL YOUR MCP SERVERS FROM ONE APP. Start, stop, or switch MCP servers instantly. Use the same MCP toolset in every AI app — no re-adding, no hassle. Stop wasting time configuring MCP servers again and again. Without MCP Bundler, every MCP client needs its own server setup. Iv every AI app with MCP support. MCP Bundler centralizes all your MCP servers — toggle, group, turn off capabilities instantly. Switch bundles on the fly inside the MCP Bundler.

Enables AI tools to interact with ConfigCat, a feature flag service for teams. Supports managing ConfigCat feature flags, configs, environments, products and organizations. Helps to integrate ConfigCat SDK, implement feature flags and remove zombie (stale) flags.

A Maritime Routing MCP Server that computes sea routes and geodesic distances using searoute and geopy. Built for maritime operations and research.

An MCP server that connects ZetaChain CLI into your editor. Query balances, send cross-chain transactions, and manage universal contracts directly through MCP.

Magic-API MCP Server - A Model Context Protocol server for Magic-API development

The Box MCP server allows third party AI agents to securely and seamlessly access Box content and use tools such as search, asking questions from files and folders, and data extraction.

AI assistants are powerful, but sometimes you still need the human touch — a real expert who understands your exact challenge and can solve it fast. That’s where GoPluto.ai comes in. GoPluto is the quick commerce of services, designed to connect you with the right live expert in minutes. Whether you’re stuck on a technical issue, need business guidance, or want creative input, simply Ask Pluto. Our system instantly matches you with verified service providers who can step in and resolve your problem on the spot. With GoPluto, you get the best of both worlds: ⚡ AI-powered discovery to surface the right context, categories, and providers 👨‍💻 Human expertise on demand, available in under 60 seconds 🔄 Seamless integration with your workflows — no switching tools or wasting time ✅ Verified knowledge and real solutions, not hallucinations or outdated docs GoPluto.ai = AI speed + human expertise. From query → expert → solution, all in minutes.

Bridge the gap between design and code. Send pixel-perfect website components directly to Cursor or Claude Code using Model Context Protocol (MCP). No more screenshots or descriptions needed.

The Octopus MCP Server provides your AI assistant with powerful tools that allow it to inspect, query, and diagnose problems within your Octopus instance, transforming it into your ultimate DevOps wingmate.

Server for managing your Gelato POD account.

MCP Server for Driflyte (https://console.driflyte.com). The Driflyte MCP Server exposes tools that allow AI assistants to query and retrieve topic-specific knowledge from recursively crawled and indexed web pages. With this MCP server, Driflyte acts as a bridge between diverse, topic-aware content sources (web, GitHub, and more) and AI-powered reasoning, enabling richer, more accurate answers.

这是一个查询天气的mcp server项目：通过调用官网数据，获取城市的经纬度，然后再调用天气查询网站，获得天气预报。

A Model Context Protocol (MCP) server that provides access to the Israeli transport api. This is the Unofficial MCP of Bus Nearby API,

Educational Python refactoring assistant with guided suggestions for AI assistants

Educational Python refactoring assistant with guided suggestions for AI assistants

Unified Context Layer (UCL) is a multi-tenant Model Context Protocol (MCP) server that enables AI agents, automation platforms, and applications to connect to over 1,000 SaaS tools—such as Slack, Jira, Gmail, Shopify, Notion, and more—via a single standardized /command endpoint. UCL abstracts away SDK sprawl, glue code, and complex authentication flows, allowing developers to orchestrate context-rich, cross-platform integrations without building and maintaining separate connectors for each service.

Scalekit Model Context Protocol (MCP) server provides comprehensive tools for managing environments, organizations, users, connections, and workspace operations. Built for developers who want to connect their AI tools to Scalekit context and capabilities based on simple natural language queries. This MCP server enables AI assistants to interact with Scalekit’s identity and access management platform through a standardized set of tools. It provides secure, OAuth-protected access to manage environments, organizations, users, authentication connections, and more. Features Environment management and configuration Organization and user management Workspace member administration OIDC connection setup and management MCP server registration and configuration Role and scope management Admin portal link generation Configuration The Scalekit MCP server can be configured to support OAuth for compatible clients. If your MCP Client doesn’t support OAuth based authorization for MCP Servers, you can still use the Scalekit MCP server with the mcp-remote acting as a local proxy to add OAuth support. ## using OAuth: { "servers": { "scalekit": { "type": "http", "url": "https://mcp.scalekit.com/" } } } ## using mcp-remote: { "mcpServers": { "scalekit": { "command": "npx", "args": ["-y", "mcp-remote", "https://mcp.scalekit.com/"] } } }

Official MCP server for Teamwork.com.

MCP server for handling large openapi specs

The official local MCP server for Kintone.

Add Two Number

A MCP server to send notification when task finish.

Crawlbase Web MCP Server (Model Context Protocol) connects AI agents and large language models (LLMs) with real-time web data. Built on Crawlbase’s proven web scraping and crawling infrastructure, it handles JavaScript rendering, anti-bot protection, and web data extraction at scale — powering Claude, Cursor, and Windsurf. It delivers a reliable, production-ready pipeline of live, structured data for AI workflows and intelligent applications.

MCP Ambari API is a powerful Model Context Protocol (MCP) server that enables seamless Apache Ambari cluster management through natural language commands. Built for DevOps engineers, data engineers, and system administrators who work with Hadoop ecosystems.

WooCommerce MCP Server Plugin (no external server needed): Connect your WooCommerce store to AI assistants like Claude and VS Code. This WordPress plugin enables AI clients to access your store's product catalog, categories, reviews, and content through a secure, read-only interface. MCP for WooCommerce transforms your WordPress site into an AI-accessible data source built on Automattic's official WordPress MCP. It safely exposes public store information—products, categories, tags, reviews, shipping options, and WordPress content—while protecting customer data and private details. Perfect for building AI-powered shopping assistants or integrating with custom AI applications.

Advanced Local Prompt Intelligence Engine with complete privacy and sophisticated content analysis. Features cross-platform support (Windows, macOS, Linux), binary optimization, and dual-tier processing: AI-aware rules engine + optional LLM enhancement. 100% local processing ensures complete privacy - no data transmission during optimization. Key Features: - Privacy-First: Complete local processing, no cloud dependencies - Cross-Platform: Native binaries for Windows, macOS (Intel/Apple Silicon), Linux (x64/ARM64) - Dual Optimization: Sophisticated rules engine + optional OpenAI LLM enhancement - Professional Tools: 50+ optimization techniques for technical and creative prompts - Template Management: Save, search, and reuse optimization patterns - Zero Setup: Works offline with cached license validation Perfect for developers, teams, and anyone requiring private prompt optimization without cloud dependencies.

An MCP server for integrating with Twenty CRM, providing access to Twenty's REST API through categorized tools. The available tools map the entire Twenty REST API and were generated using the openapi-mcp-generator.

🚀 The ONLY browser automation that bypasses Cloudflare, antibots, and social media blocks. Supercharge any MCP-compatible AI agent with undetectable, real-browser automation. No CAPTCHAs. No blocks. Just results.⚡ 30-second setup • 🛡️ Undetectable by design • 🏆 98.7% success rate on protected sites • 🕵️ Full network debugging via AI chat Features: Works on protected sites that block traditional automation- Pixel-accurate element cloning via Chrome DevTools Protocol - Full network debugging through AI chat — see every request, response, header, and payload- Your AI agent becomes a network detective — no more guessing what APIs are being called- 🎛️ Modular architecture — disable unused sections, run minimal installs- ⚡ Lightweight deployments — from 21 core tools to full 88-tool arsenal- Clean MCP integration — no custom brokers or wrappers needed- 88 focused tools organized into 11 logical sections

Clipboard MCP Server An MCP server that allows LLM models to save relevant output directly to your system clipboard for immediate use.

pushplus 推送加 MCP Server TypeScript版 实现了pushplus的消息推送接口

A complete Twitter API MCP server implementation based on the API endpoints provided by twitterapi.io. 一个完整的Twitter API MCP服务器，基于twitterapi.io提供的API端点实现。

A Model Context Protocol (MCP) server for comprehensive image editing operations including resizing, format conversion, cropping, compression, and more.

Performs pseudo-anonymization rather than redaction to preserve semantic meaning and data relationships required for AI analysis. Example: john.smith@acme.com becomes mike.wilson@techcorp.com, maintaining structure while protecting sensitive information.

A Model Context Protocol (MCP) server that provides access to the Philippine Standard Geographic Code (PSGC) API, offering hierarchical geographic data for the Philippines.

Unofficial MCP Server for Qiskit (an open-source SDK for working with quantum computers)

A Model Context Protocol (MCP) server for interacting with Octopus Deploy. This server provides tools for managing projects, releases, and deployments through the MCP protocol. Features Project Management: List and query Octopus Deploy projects Release Management: Get latest releases and create new releases Deployment Management: Deploy releases and check deployment status Multi-Space Support: Work with different Octopus Deploy spaces Docker Support: Containerized deployment for easy integration

The Signoz MCP Server lets you connect developer tools like Cursor or Claude Desktop to your Signoz instance. It's an open-source project maintained by DrDroid (not affiliated with Signoz), and allows you to query logs, dashboards, metrics, and more — making observability data directly accessible within your IDE or AI assistant.

Comprehensive MCP server providing real-time framework documentation access for Claude Code with intelligent caching, multi-source integration, and context-aware assistance.

A comprehensive JSON Schema validation server implementing the Model Context Protocol (MCP) with support for JSON Schema Draft 2020-12, external references, schema management, and real-time streaming validation.

A Model Context Protocol (MCP) server that provides seamless integration with the Judgment API for AI evaluation workflows. This server enables you to manage datasets, run evaluations, and track traces directly from your MCP-compatible environment.

A Model Context Protocol (MCP) server that provides programmatic access to Israeli Land Authority (רמ״י) public tender data.

# HomeyPro MCP Server A Model Context Protocol (MCP) server for interacting with HomeyPro home automation systems. This server provides paginated access to devices, zones, and flows with comprehensive management capabilities. ## Features - **Device Management**: List, search, and control devices with full capability support - **Zone Management**: Browse zones and their associated devices - **Flow Management**: List and trigger automation flows - **System Management**: Get and update system configuration (location, address, language, units) - **AI-Powered Prompts**: Context-aware guidance for device control, troubleshooting, and automation - **Resource Caching**: Efficient data access with intelligent caching and stale data fallback - **Pagination Support**: Efficient handling of large datasets with cursor-based pagination - **Real-time Data**: Get current device states, capabilities, and insights - **Error Handling**: Comprehensive error handling with detailed error messages ## Installation ### Local Development 1. Clone the repository and navigate to the project directory: ```bash cd python-homey-mcp ``` 2. Install dependencies using uv: ```bash uv sync ``` ### Docker Pull the pre-built Docker image: ```bash docker pull ghcr.io/pigmej/python-homey-mcp:latest ``` No additional installation steps are required when using Docker. ## Configuration Before running the server, you need to configure your HomeyPro connection: ### Environment Variables Set the following environment variables: ```bash export HOMEY_API_URL="http://YOUR_HOMEY_IP_ADDRESS" export HOMEY_API_TOKEN="YOUR_PERSONAL_ACCESS_TOKEN" ``` ### Getting Your HomeyPro Token 1. Open the HomeyPro web interface 2. Go to Settings > General > API 3. Create a new Personal Access Token 4. Copy the token and set it as the `HOMEY_API_TOKEN` environment variable ### Finding Your HomeyPro IP Address You can find your HomeyPro's IP address in: - HomeyPro web interface: Settings > General > Network - Your router's admin panel - HomeyPro mobile app: More > Settings > General > Network ## Usage ### Running the Server #### Local Development ```bash uv run fastmcp run -t http --host 0.0.0.0 -p 4445 -l DEBUG main.py ``` #### Docker Container Run the MCP server in a Docker container: ```bash docker run -p 4445:4445 \ -e HOMEY_API_URL="http://YOUR_HOMEY_IP_ADDRESS" \ -e HOMEY_API_TOKEN="YOUR_PERSONAL_ACCESS_TOKEN" \ ghcr.io/pigmej/python-homey-mcp:latest ``` Or using docker-compose: ```yaml version: '3.8' services: python-homey-mcp: image: ghcr.io/pigmej/python-homey-mcp:latest ports: - "4445:4445" environment: - HOMEY_API_URL=http://YOUR_HOMEY_IP_ADDRESS - HOMEY_API_TOKEN=YOUR_PERSONAL_ACCESS_TOKEN ``` The server will start and connect to your HomeyPro instance. You'll see a connection confirmation message. But basically please yield to [FastMCP docs](https://gofastmcp.com/patterns/cli) ## AI-Powered Prompts The server provides context-aware prompts that help you interact with your HomeyPro system more effectively. These prompts analyze your current system state and provide tailored guidance. ### Available Prompts #### Device Control Assistant Provides structured guidance for controlling different types of devices in your HomeyPro system. - **Context**: Current device counts, online/offline status, available device types - **Guidance**: Control patterns for lighting, climate, security, and entertainment devices - **Best Practices**: Device status checking, capability usage, troubleshooting tips #### Device Troubleshooting Systematic diagnostic guidance for common HomeyPro device issues. - **System Health**: Overall device health percentage and status indicators - **Step-by-Step Process**: Structured troubleshooting workflow - **Device-Specific**: Targeted solutions for offline and unresponsive devices - **Advanced Diagnostics**: Network, performance, and system-level troubleshooting #### Device Capability Explorer Helps you discover and understand device capabilities without overwhelming detail. - **Capability Categories**: Control, sensor, and status capabilities - **Value Types**: Boolean, numeric, string, and enum capability formats - **Usage Patterns**: Common capability combinations and best practices - **Device Type Patterns**: Capability patterns for different device categories #### Flow Creation Assistant Structured guidance for creating HomeyPro automation flows. - **Flow Framework**: WHEN (trigger), AND (conditions), THEN (actions) structure - **Common Scenarios**: Security, comfort, energy, convenience, and safety automations - **System Context**: Available zones, device types, and existing flows - **Templates**: Ready-to-use flow templates for common use cases #### Flow Optimization Guidance for improving existing flow performance and reliability. - **Performance Analysis**: Flow execution patterns and optimization opportunities - **Resource Usage**: Device and system resource considerations - **Best Practices**: Flow organization, naming, and maintenance strategies #### Flow Debugging Systematic approach to diagnosing and fixing flow issues. - **Common Problems**: Flow execution failures, timing issues, device conflicts - **Diagnostic Tools**: Log analysis, condition testing, action verification - **Resolution Strategies**: Step-by-step debugging workflow #### System Health Check Comprehensive system health analysis and recommendations. - **Health Indicators**: Device connectivity, flow status, system performance - **Status Overview**: Connection status, system configuration, resource usage - **Recommendations**: Maintenance suggestions and optimization opportunities #### Zone Organization Guidance for organizing and optimizing zone structure. - **Zone Planning**: Logical grouping strategies for devices and areas - **Hierarchy Management**: Parent-child zone relationships - **Device Assignment**: Best practices for device-to-zone mapping ### Prompt Features - **Context-Aware**: All prompts analyze your current system state - **Real-Time Data**: Information is based on current device and system status - **Graceful Degradation**: Prompts work even when HomeyPro is temporarily unavailable - **Error Handling**: Clear error messages with suggested actions - **Actionable Guidance**: Practical steps you can take immediately ## Resource Caching The server provides intelligent resource caching with automatic fallback to stale data when HomeyPro is temporarily unavailable. ### Available Resources #### System Overview (`homey://system/overview`) Comprehensive system overview including device counts, zone counts, and health indicators. - **Content**: Device statistics, zone summary, system health percentage - **Cache TTL**: 5 minutes - **Use Case**: Dashboard displays, system monitoring, health checks #### Device Registry (`homey://devices/registry`) Complete device inventory with current states, capabilities, and online/offline indicators. - **Content**: Full device list with capabilities, states, and metadata - **Cache TTL**: 30 seconds (dynamic data) - **Use Case**: Device management interfaces, capability discovery, status monitoring #### Zone Hierarchy (`homey://zones/hierarchy`) Zone structure with device associations and parent-child relationships. - **Content**: Zone tree, device assignments, zone types and statistics - **Cache TTL**: 5 minutes - **Use Case**: Zone management, device organization, spatial automation #### Flow Catalog (`homey://flows/catalog`) Available flows with metadata, status, and execution statistics. - **Content**: Flow list with triggers, conditions, actions, and execution data - **Cache TTL**: 2 minutes - **Use Case**: Flow management, automation analysis, debugging ### Caching Features - **Intelligent TTL**: Different cache durations based on data volatility - **Stale Data Fallback**: Returns cached data when HomeyPro is unreachable - **Error Handling**: Graceful degradation with detailed error information - **Connection Resilience**: Continues operation during network issues - **Performance Optimization**: Reduces API calls and improves response times ### Cache Behavior 1. **Fresh Data**: Returns current data when cache is valid and HomeyPro is accessible 2. **Stale Data**: Returns cached data with staleness indicators when HomeyPro is unreachable 3. **Error Response**: Returns structured error information when no cached data is available 4. **Automatic Refresh**: Cache automatically refreshes when HomeyPro becomes available again ## API Tools The server provides comprehensive API tools for direct HomeyPro interaction. All tools support pagination and error handling with detailed responses. ### Device Tools #### Device Discovery and Information - **`list_devices`**: List all devices with pagination support - Optional compact mode for reduced data transfer - Excludes hidden devices automatically - Includes online/offline status for each device - **`get_device`**: Get detailed information about a specific device - Complete device details including capabilities and settings - Capability values and detailed configuration - Energy information and UI settings - **`get_devices_classes`**: List all available device classes - Useful for understanding device types before searching - Returns complete list of supported device categories - **`get_devices_capabilities`**: List all possible device capabilities - Comprehensive capability reference - Essential for understanding control options #### Device Search and Filtering - **`search_devices_by_name`**: Search devices by name with pagination - Fuzzy matching against device names - Includes note field information for context - Supports pagination for large result sets - **`search_devices_by_class`**: Search devices by class/type - Filter devices by specific categories (lights, sensors, etc.) - Paginated results with metadata #### Device Control and Monitoring - **`control_device`**: Control device capabilities - Set capability values (on/off, dimming, temperature, etc.) - JSON value parsing with fallback handling - Returns current device state after control - **`get_device_insights`**: Get historical device data - Multiple time resolutions (hour, day, week, month) - Custom timestamp ranges supported - Capability-specific insights and trends ### Zone Tools #### Zone Management - **`list_zones`**: List all zones with pagination - Complete zone hierarchy information - Parent-child relationships included - **`get_zone_devices`**: Get all devices in a specific zone - Zone-based device filtering - Compact mode option for performance - Online/offline status per device #### Zone Monitoring - **`get_zone_temp`**: Get average temperature for a zone - Automatically averages temperature sensors in the zone - Handles zones without temperature sensors gracefully ### Flow Tools #### Basic Flow Management - **`list_flows`**: List all standard flows with pagination - Complete flow metadata and configuration - Trigger, condition, and action information - **`trigger_flow`**: Execute a specific flow - Manual flow triggering - Success confirmation with flow details - **`get_flow_folders`**: Get all flow organization folders - Flow organization structure - Folder hierarchy for better management - **`get_flows_by_folder`**: Get flows in a specific folder - Folder-based flow filtering - Organizational flow management - **`get_flows_without_folder`**: Get unorganized flows - Find flows that need organization - Cleanup and maintenance assistance #### Advanced Flow Management - **`list_advanced_flows`**: List all advanced flows - Complex automation flows with scripting - Complete flow structure and metadata - **`get_advanced_flow`**: Get detailed advanced flow information - Full flow configuration and logic - Script content and execution details - **`trigger_advanced_flow`**: Execute advanced flows - Manual triggering of complex automations - Execution confirmation and status #### Advanced Flow Search and Filtering - **`search_advanced_flows`**: Search advanced flows by name/description - Text-based flow discovery - Paginated search results - **`get_enabled_advanced_flows`**: Get only enabled advanced flows - Active automation discovery - Performance and maintenance insights - **`get_disabled_advanced_flows`**: Get disabled advanced flows - Inactive flow identification - Maintenance and cleanup assistance - **`get_broken_advanced_flows`**: Get flows with errors - Error detection and troubleshooting - System health monitoring - **`get_advanced_flows_by_folder`**: Get advanced flows in folders - Organized advanced flow management - Folder-based filtering - **`get_advanced_flows_without_folder`**: Get unorganized advanced flows - Organization and cleanup assistance - Flow management optimization - **`get_advanced_flows_with_inline_scripts`**: Get flows containing scripts - Script-based automation identification - Advanced functionality discovery #### Flow State Management - **`enable_advanced_flow`**: Enable a disabled advanced flow - Flow activation with confirmation - State management and control - **`disable_advanced_flow`**: Disable an active advanced flow - Flow deactivation for maintenance - Temporary automation suspension ### System Tools #### System Information - **`get_system_info`**: Get comprehensive system overview - Connection status and system health - Device, zone, and flow counts - Online/offline device statistics - Flow status (enabled/disabled/broken) - System configuration (address, language, units) - Location coordinates and regional settings - Recommended as first call before other operations ### Tool Features #### Pagination Support - **Cursor-based pagination**: Efficient handling of large datasets - **Configurable page sizes**: Optimize for your use case - **Total count tracking**: Know the full dataset size - **Next page indicators**: Easy navigation through results #### Data Formats - **Compact mode**: Reduced data transfer for performance - **Full detail mode**: Complete information when needed - **JSON value handling**: Automatic parsing with fallbacks - **Error responses**: Structured error information with details #### Performance Optimization - **Hidden device filtering**: Automatic exclusion of system devices - **Efficient queries**: Optimized API calls to HomeyPro - **Connection reuse**: Persistent connections for better performance - **Graceful degradation**: Continues operation during partial failures #### Error Handling - **Detailed error messages**: Clear problem descriptions - **Connection status**: Network and API health indicators - **Fallback responses**: Graceful handling of API failures - **Logging integration**: Comprehensive error tracking ### Contributing 1. Fork the repository 2. Create a feature branch 3. Make your changes 4. Add tests if applicable 5. Submit a pull request ## License This project is licensed under the MIT License.