From 4f611634e8b0a87c2cc4a7ad10133b27e06e196f Mon Sep 17 00:00:00 2001 From: Quentin Cody Date: Wed, 20 Aug 2025 17:34:37 -0400 Subject: [PATCH 01/11] Add 12 bioinformatics and research MCP servers to community section - Add CIViC MCP server for clinical variant interpretation - Add DataCite MCP server for research data and publication metadata - Add DGIdb MCP server for drug-gene interaction data - Add Entrez MCP server for NCBI biomedical databases - Add NCI GDC MCP server for cancer genomic data - Add OpenNeuro MCP server for open neuroimaging datasets - Add Open Targets MCP server for target-disease associations - Add Pharos MCP server for target, drug, and disease information - Add RCSB PDB MCP server for 3D protein structures - Add UniProt MCP server for protein sequence and functional data - Add Wikidata SPARQL MCP server for structured knowledge queries - Add ZincBind MCP server for zinc binding sites in proteins All servers added in alphabetical order following contribution guidelines. --- README.md | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/README.md b/README.md index 3c4b0be0a4..2ad4d9bf1e 100644 --- a/README.md +++ b/README.md @@ -549,6 +549,7 @@ A growing set of community-developed and maintained servers demonstrates various - **[ChessPal Chess Engine (stockfish)](https://github.com/wilson-urdaneta/chesspal-mcp-engine)** - A Stockfish-powered chess engine exposed as an MCP server. Calculates best moves and supports both HTTP/SSE and stdio transports. - **[Chroma](https://github.com/privetin/chroma)** - Vector database server for semantic document search and metadata filtering, built on Chroma - **[Chrome history](https://github.com/vincent-pli/chrome-history-mcp)** - Talk with AI about your browser history, get fun ^_^ +- **[CIViC](https://github.com/QuentinCody/civic-mcp-server)** - MCP server for the Clinical Interpretation of Variants in Cancer (CIViC) database, providing access to clinical variant interpretations and genomic evidence for cancer research. - **[Claude Thread Continuity](https://github.com/peless/claude-thread-continuity)** - Persistent memory system enabling Claude Desktop conversations to resume with full context across sessions. Maintains conversation history, project states, and user preferences for seamless multi-session workflows. - **[ClaudePost](https://github.com/ZilongXue/claude-post)** - ClaudePost enables seamless email management for Gmail, offering secure features like email search, reading, and sending. - **[CLDGeminiPDF Analyzer](https://github.com/tfll37/CLDGeminiPDF-Analyzer)** - MCP server tool enabling sharing large PDF files to Google LLMs via API for further/additional analysis and response retrieval to Claude Desktop. @@ -590,6 +591,7 @@ A growing set of community-developed and maintained servers demonstrates various - **[Databricks](https://github.com/JordiNeil/mcp-databricks-server)** - Allows LLMs to run SQL queries, list and get details of jobs executions in a Databricks account. - **[Databricks Genie](https://github.com/yashshingvi/databricks-genie-MCP)** - A server that connects to the Databricks Genie, allowing LLMs to ask natural language questions, run SQL queries, and interact with Databricks conversational agents. - **[Databricks Smart SQL](https://github.com/RafaelCartenet/mcp-databricks-server)** - Leveraging Databricks Unity Catalog metadata, perform smart efficient SQL queries to solve Ad-hoc queries and explore data. +- **[DataCite](https://github.com/QuentinCody/datacite-mcp-server)** - Unofficial MCP server for DataCite, providing access to research data and publication metadata through DataCite's REST API and GraphQL interface for scholarly research discovery. - **[Datadog](https://github.com/GeLi2001/datadog-mcp-server)** - Datadog MCP Server for application tracing, monitoring, dashboard, incidents queries built on official datadog api. - **[Dataset Viewer](https://github.com/privetin/dataset-viewer)** - Browse and analyze Hugging Face datasets with features like search, filtering, statistics, and data export - **[DataWorks](https://github.com/aliyun/alibabacloud-dataworks-mcp-server)** - A Model Context Protocol (MCP) server that provides tools for AI, allowing it to interact with the [DataWorks](https://www.alibabacloud.com/help/en/dataworks/) Open API through a standardized interface. This implementation is based on the Alibaba Cloud Open API and enables AI agents to perform cloud resources operations seamlessly. @@ -608,6 +610,7 @@ A growing set of community-developed and maintained servers demonstrates various - **[DevDb](https://github.com/damms005/devdb-vscode?tab=readme-ov-file#mcp-configuration)** - An MCP server that runs right inside the IDE, for connecting to MySQL, Postgres, SQLite, and MSSQL databases. - **[DevOps AI Toolkit](https://github.com/vfarcic/dot-ai)** - AI-powered development productivity platform that enhances software development workflows through intelligent automation and AI-driven assistance. - **[DevOps-MCP](https://github.com/wangkanai/devops-mcp)** - Dynamic Azure DevOps MCP server with directory-based authentication switching, supporting work items, repositories, builds, pipelines, and multi-project management with local configuration files. +- **[DGIdb](https://github.com/QuentinCody/dgidb-mcp-server)** - MCP server for the Drug Gene Interaction Database (DGIdb), providing access to drug-gene interaction data, druggable genome information, and pharmacogenomics research. - **[Dicom](https://github.com/ChristianHinge/dicom-mcp)** - An MCP server to query and retrieve medical images and for parsing and reading dicom-encapsulated documents (pdf etc.). - **[Dify](https://github.com/YanxingLiu/dify-mcp-server)** - A simple implementation of an MCP server for dify workflows. - **[Discogs](https://github.com/cswkim/discogs-mcp-server)** - An MCP server that connects to the Discogs API for interacting with your music collection. @@ -637,6 +640,7 @@ A growing set of community-developed and maintained servers demonstrates various - **[Email](https://github.com/Shy2593666979/mcp-server-email)** - This server enables users to send emails through various email providers, including Gmail, Outlook, Yahoo, Sina, Sohu, 126, 163, and QQ Mail. It also supports attaching files from specified directories, making it easy to upload attachments along with the email content. - **[Email SMTP](https://github.com/egyptianego17/email-mcp-server)** - A simple MCP server that lets your AI agent send emails and attach files through SMTP. - **[Enhance Prompt](https://github.com/FelixFoster/mcp-enhance-prompt)** - An MCP service for enhance you prompt. +- **[Entrez](https://github.com/QuentinCody/entrez-mcp-server)** - Unofficial MCP server for NCBI Entrez databases, providing access to PubMed articles, gene information, protein data, and other biomedical research resources through NCBI's E-utilities API. - **[Ergo Blockchain MCP](https://github.com/marctheshark3/ergo-mcp)** -An MCP server to integrate Ergo Blockchain Node and Explorer APIs for checking address balances, analyzing transactions, viewing transaction history, performing forensic analysis of addresses, searching for tokens, and monitoring network status. - **[ESP MCP Server](https://github.com/horw/esp-mcp)** - An MCP server that integrates ESP IDF commands like building and flashing code for ESP Microcontrollers using an LLM. - **[Eunomia](https://github.com/whataboutyou-ai/eunomia-MCP-server)** - Extension of the Eunomia framework that connects Eunomia instruments with MCP servers @@ -913,6 +917,7 @@ A growing set of community-developed and maintained servers demonstrates various - **[NAVER](https://github.com/pfldy2850/py-mcp-naver)** (by pfldy2850) - This MCP server provides tools to interact with various Naver services, such as searching blogs, news, books, and more. - **[Naver](https://github.com/isnow890/naver-search-mcp)** (by isnow890) - MCP server for Naver Search API integration, supporting blog, news, shopping search and DataLab analytics features. - **[NBA](https://github.com/Taidgh-Robinson/nba-mcp-server)** - This MCP server provides tools to fetch recent and historical NBA games including basic and advanced statistics. +- **[NCI GDC](https://github.com/QuentinCody/nci-gdc-mcp-server)** - Unofficial MCP server for the National Cancer Institute's Genomic Data Commons (GDC), providing access to harmonized cancer genomic and clinical data for oncology research. - **[Neo4j](https://github.com/da-okazaki/mcp-neo4j-server)** - A community built server that interacts with Neo4j Graph Database. - **[Neovim](https://github.com/bigcodegen/mcp-neovim-server)** - An MCP Server for your Neovim session. - **[Netbird](https://github.com/aantti/mcp-netbird)** - List and analyze Netbird network peers, groups, policies, and more. @@ -954,9 +959,11 @@ A growing set of community-developed and maintained servers demonstrates various - **[OpenLink Generic Python Open Database Connectivity](https://github.com/OpenLinkSoftware/mcp-pyodbc-server)** - Generic Database Management System (DBMS) access via Open Database Connectivity (ODBC) Connectors (Drivers) for PyODBC - **[OpenLink Generic SQLAlchemy Object-Relational Database Connectivity for PyODBC](https://github.com/OpenLinkSoftware/mcp-sqlalchemy-server)** - Generic Database Management System (DBMS) access via SQLAlchemy (PyODBC) Connectors (Drivers) - **[OpenMetadata](https://github.com/yangkyeongmo/mcp-server-openmetadata)** - MCP Server for OpenMetadata, an open-source metadata management platform. +- **[OpenNeuro](https://github.com/QuentinCody/open-neuro-mcp-server)** - Unofficial MCP server for OpenNeuro, providing access to open neuroimaging datasets, study metadata, and brain imaging data for neuroscience research and analysis. - **[OpenReview](https://github.com/anyakors/openreview-mcp-server)** - An MCP server for [OpenReview](https://openreview.net/) to fetch, read and save manuscripts from AI/ML conferences. - **[OpenRPC](https://github.com/shanejonas/openrpc-mpc-server)** - Interact with and discover JSON-RPC APIs via [OpenRPC](https://open-rpc.org). - **[OpenStack](https://github.com/wangsqly0407/openstack-mcp-server)** - MCP server implementation that provides OpenStack interaction. +- **[Open Targets](https://github.com/QuentinCody/open-targets-mcp-server)** - Unofficial MCP server for the Open Targets Platform, providing access to target-disease associations, drug discovery data, and therapeutic hypothesis generation for biomedical research. - **[OpenWeather](https://github.com/mschneider82/mcp-openweather)** - Interact with the free openweathermap API to get the current and forecast weather for a location. - **[Operative WebEvalAgent](https://github.com/Operative-Sh/web-eval-agent)** (by [Operative.sh](https://www.operative.sh)) - An MCP server to test, debug, and fix web applications autonomously. - **[OPNSense MCP](https://github.com/vespo92/OPNSenseMCP)** - MCP Server for OPNSense Firewall Management and API access @@ -978,6 +985,7 @@ A growing set of community-developed and maintained servers demonstrates various - **[PDMT](https://github.com/paiml/pdmt)** - Pragmatic Deterministic MCP Templating - High-performance deterministic templating library with comprehensive todo validation, quality enforcement, and 0.0 temperature generation for reproducible outputs. - **[Peacock for VS Code](https://github.com/johnpapa/peacock-mcp)** - MCP Server for the Peacock extension for VS Code, coloring your world, one Code editor at a time. The main goal of the project is to show how an MCP server can be used to interact with APIs. - **[persistproc](https://github.com/irskep/persistproc)** - MCP server + command line tool that allows agents to see & control long-running processes like web servers. +- **[Pharos](https://github.com/QuentinCody/pharos-mcp-server)** - Unofficial MCP server for the Pharos database by the National Center for Advancing Translational Sciences (NCATS), providing access to target, drug, and disease information for drug discovery research. - **[Phone MCP](https://github.com/hao-cyber/phone-mcp)** - 📱 A powerful plugin that lets you control your Android phone. Enables AI agents to perform complex tasks like automatically playing music based on weather or making calls and sending texts. - **[PIF](https://github.com/hungryrobot1/MCP-PIF)** - A Personal Intelligence Framework (PIF), providing tools for file operations, structured reasoning, and journal-based documentation to support continuity and evolving human-AI collaboration across sessions. - **[Pinecone](https://github.com/sirmews/mcp-pinecone)** - MCP server for searching and uploading records to Pinecone. Allows for simple RAG features, leveraging Pinecone's Inference API. @@ -1015,6 +1023,7 @@ A growing set of community-developed and maintained servers demonstrates various - **[RAG Web Browser](https://github.com/apify/mcp-server-rag-web-browser)** An MCP server for Apify's open-source RAG Web Browser [Actor](https://apify.com/apify/rag-web-browser) to perform web searches, scrape URLs, and return content in Markdown. - **[Raindrop.io](https://github.com/hiromitsusasaki/raindrop-io-mcp-server)** - An integration that allows LLMs to interact with Raindrop.io bookmarks using the Model Context Protocol (MCP). - **[Random Number](https://github.com/zazencodes/random-number-mcp)** - Provides LLMs with essential random generation abilities, built entirely on Python's standard library. +- **[RCSB PDB](https://github.com/QuentinCody/rcsb-pdb-mcp-server)** - Unofficial MCP server for the Research Collaboratory for Structural Bioinformatics Protein Data Bank (RCSB PDB), providing access to 3D protein structures, experimental data, and structural bioinformatics information. - **[Reaper](https://github.com/dschuler36/reaper-mcp-server)** - Interact with your [Reaper](https://www.reaper.fm/) (Digital Audio Workstation) projects. - **[Redbee](https://github.com/Tamsi/redbee-mcp)** - Redbee MCP server that provides support for interacting with Redbee API. - **[Redis](https://github.com/GongRzhe/REDIS-MCP-Server)** - Redis database operations and caching microservice server with support for key-value operations, expiration management, and pattern-based key listing. @@ -1133,6 +1142,7 @@ A growing set of community-developed and maintained servers demonstrates various - **[Tyk API Management](https://github.com/TykTechnologies/tyk-dashboard-mcp)** - Chat with all of your organization's managed APIs and perform other API lifecycle operations, managing tokens, users, analytics, and more. - **[Typesense](https://github.com/suhail-ak-s/mcp-typesense-server)** - A Model Context Protocol (MCP) server implementation that provides AI models with access to Typesense search capabilities. This server enables LLMs to discover, search, and analyze data stored in Typesense collections. - **[UniFi Dream Machine](https://github.com/sabler/mcp-unifi)** An MCP server that gets your network telemetry from the UniFi Site Manager and your local UniFi router. +- **[UniProt](https://github.com/QuentinCody/uniprot-mcp-server)** - Unofficial MCP server for UniProt, providing access to protein sequence data, functional annotations, taxonomic information, and cross-references for proteomics and bioinformatics research. - **[uniswap-poolspy-mcp](https://github.com/kukapay/uniswap-poolspy-mcp)** - An MCP server that tracks newly created liquidity pools on Uniswap across nine blockchain networks. - **[uniswap-trader-mcp](https://github.com/kukapay/uniswap-trader-mcp)** -An MCP server for AI agents to automate token swaps on Uniswap DEX across multiple blockchains. - **[Unity Catalog](https://github.com/ognis1205/mcp-server-unitycatalog)** - An MCP server that enables LLMs to interact with Unity Catalog AI, supporting CRUD operations on Unity Catalog Functions and executing them as MCP tools. @@ -1167,6 +1177,7 @@ A growing set of community-developed and maintained servers demonstrates various - **[WhatsApp MCP Server](https://github.com/lharries/whatsapp-mcp)** - MCP server for your personal WhatsApp handling individuals, groups, searching and sending. - **[Whois MCP](https://github.com/bharathvaj-ganesan/whois-mcp)** - MCP server that performs whois lookup against domain, IP, ASN and TLD. - **[Wikidata MCP](https://github.com/zzaebok/mcp-wikidata)** - Wikidata MCP server that interact with Wikidata, by searching identifiers, extracting metadata, and executing sparql query. +- **[Wikidata SPARQL](https://github.com/QuentinCody/wikidata-sparql-mcp-server)** - Unofficial REMOTE MCP server for Wikidata's SPARQL endpoint, providing access to structured knowledge data, entity relationships, and semantic queries for research and data analysis. - **[Wikipedia MCP](https://github.com/Rudra-ravi/wikipedia-mcp)** - Access and search Wikipedia articles via MCP for AI-powered information retrieval. - **[WildFly MCP](https://github.com/wildfly-extras/wildfly-mcp)** - WildFly MCP server that enables LLM to interact with running WildFly servers (retrieve metrics, logs, invoke operations, ...). - **[Windows CLI](https://github.com/SimonB97/win-cli-mcp-server)** - MCP server for secure command-line interactions on Windows systems, enabling controlled access to PowerShell, CMD, and Git Bash shells. @@ -1195,6 +1206,7 @@ A growing set of community-developed and maintained servers demonstrates various - **[YouTube Video Summarizer](https://github.com/nabid-pf/youtube-video-summarizer-mcp)** - Summarize lengthy youtube videos. - **[yutu](https://github.com/eat-pray-ai/yutu)** - A fully functional MCP server and CLI for YouTube to automate YouTube operation. - **[ZapCap](https://github.com/bogdan01m/zapcap-mcp-server)** - MCP server for ZapCap API providing video caption and B-roll generation via natural language +- **[ZincBind](https://github.com/QuentinCody/zincbind-mcp-server)** - Unofficial MCP server for ZincBind, providing access to a comprehensive database of zinc binding sites in proteins, structural coordination data, and metalloproteomics research information. - **[Zoom](https://github.com/Prathamesh0901/zoom-mcp-server/tree/main)** - Create, update, read and delete your zoom meetings. ## 📚 Frameworks From 11d9d6caf82c3f64f99c80ae206983697fb29bdb Mon Sep 17 00:00:00 2001 From: Prathit <67639393+Prat011@users.noreply.github.com> Date: Thu, 21 Aug 2025 05:09:22 +0000 Subject: [PATCH 02/11] feat: add Rube MCP server to the readme --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 3c4b0be0a4..81d434250c 100644 --- a/README.md +++ b/README.md @@ -367,6 +367,7 @@ Official integrations are maintained by companies building production ready MCP - Rodin **[Rodin](https://github.com/DeemosTech/rodin-api-mcp)** - Generate 3D Models with [Hyper3D Rodin](https://hyper3d.ai) - Root Signals Logo **[Root Signals](https://github.com/root-signals/root-signals-mcp)** - Improve and quality control your outputs with evaluations using LLM-as-Judge - **[Routine](https://github.com/routineco/mcp-server)** - MCP server to interact with [Routine](https://routine.co/): calendars, tasks, notes, etc. +- Composio Logo **[Rube](https://rube.composio.dev)** - Rube is a Model Context Protocol (MCP) server that connects your AI tools to 500+ apps like Gmail, Slack, GitHub, and Notion. Simply install it in your AI client, authenticate once with your apps, and start asking your AI to perform real actions like "Send an email" or "Create a task." - SafeDep Logo **[SafeDep](https://github.com/safedep/vet/blob/main/docs/mcp.md)** - SafeDep `vet-mcp` helps in vetting open source packages for security risks—such as vulnerabilities and malicious code—before they're used in your project, especially with AI-generated code suggestions. - SafeLine Logo **[SafeLine](https://github.com/chaitin/SafeLine/tree/main/mcp_server)** - [SafeLine](https://safepoint.cloud/landing/safeline) is a self-hosted WAF(Web Application Firewall) to protect your web apps from attacks and exploits. - ScrAPI Logo **[ScrAPI](https://github.com/DevEnterpriseSoftware/scrapi-mcp)** - Web scraping using [ScrAPI](https://scrapi.tech). Extract website content that is difficult to access because of bot detection, captchas or even geolocation restrictions. From f1b4fd285628dc84597863b194c0552b42eeb189 Mon Sep 17 00:00:00 2001 From: doobidoo Date: Fri, 22 Aug 2025 07:40:20 +0200 Subject: [PATCH 03/11] Add MCP Context Provider to community servers list Add MCP Context Provider to the Third-Party Servers section in alphabetical order. This server provides AI models with persistent tool-specific context and rules, preventing context loss between chat sessions. --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 19f5cbb8c3..5e2a2ea7c3 100644 --- a/README.md +++ b/README.md @@ -578,6 +578,7 @@ A growing set of community-developed and maintained servers demonstrates various - **[consult7](https://github.com/szeider/consult7)** - Analyze large codebases and document collections using high-context models via OpenRouter, OpenAI, or Google AI -- very useful, e.g., with Claude Code - **[Contentful-mcp](https://github.com/ivo-toby/contentful-mcp)** - Read, update, delete, publish content in your [Contentful](https://contentful.com) space(s) from this MCP Server. - **[Context Crystallizer](https://github.com/hubertciebiada/context-crystallizer)** - AI Context Engineering tool that transforms large repositories into crystallized, AI-consumable knowledge through systematic analysis and optimization. +- **[MCP Context Provider](https://github.com/doobidoo/MCP-Context-Provider)** - Static server that provides AI models with persistent tool-specific context and rules, preventing context loss between chat sessions and enabling consistent behavior across interactions. - **[context-portal](https://github.com/GreatScottyMac/context-portal)** - Context Portal (ConPort) is a memory bank database system that effectively builds a project-specific knowledge graph, capturing entities like decisions, progress, and architecture, along with their relationships. This serves as a powerful backend for Retrieval Augmented Generation (RAG), enabling AI assistants to access precise, up-to-date project information. - **[cplusplus-mcp](https://github.com/kandrwmrtn/cplusplus_mcp)** - Semantic C++ code analysis using libclang. Enables Claude to understand C++ codebases through AST parsing rather than text search - find classes, navigate inheritance, trace function calls, and explore code relationships. - **[CreateveAI Nexus](https://github.com/spgoodman/createveai-nexus-server)** - Open-Source Bridge Between AI Agents and Enterprise Systems, with simple custom API plug-in capabilities (including close compatibility with ComfyUI nodes), support for Copilot Studio's MCP agent integations, and support for Azure deployment in secure environments with secrets stored in Azure Key Vault, as well as straightforward on-premises deployment. From e7f235a6c0d7683a8b5de92b33293fad5fc5732e Mon Sep 17 00:00:00 2001 From: doobidoo Date: Fri, 22 Aug 2025 07:48:59 +0200 Subject: [PATCH 04/11] Add mcp-memory-service to community servers list Add mcp-memory-service to the Third-Party Servers section in alphabetical order. This universal memory service provides semantic search, persistent storage, and autonomous memory consolidation for AI assistants across multiple platforms. --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 5e2a2ea7c3..5801962cde 100644 --- a/README.md +++ b/README.md @@ -860,6 +860,7 @@ A growing set of community-developed and maintained servers demonstrates various - **[mcp-local-rag](https://github.com/nkapila6/mcp-local-rag)** - "primitive" RAG-like web search model context protocol (MCP) server that runs locally using Google's MediaPipe Text Embedder and DuckDuckGo Search. - **[mcp-mcp](https://github.com/wojtyniak/mcp-mcp)** - Meta-MCP Server that acts as a tool discovery service for MCP clients. - **[mcp-meme-sticky](https://github.com/nkapila6/mcp-meme-sticky)** - Make memes or stickers using MCP server for WhatsApp or Telegram. +- **[mcp-memory-service](https://github.com/doobidoo/mcp-memory-service)** - Universal MCP memory service providing semantic memory search, persistent storage, and autonomous memory consolidation for AI assistants across 13+ AI applications. - **[MCP-NixOS](https://github.com/utensils/mcp-nixos)** - A Model Context Protocol server that provides AI assistants with accurate, real-time information about NixOS packages, system options, Home Manager settings, and nix-darwin macOS configurations. - **[mcp-open-library](https://github.com/8enSmith/mcp-open-library)** - A Model Context Protocol (MCP) server for the Open Library API that enables AI assistants to search for book and author information. - **[mcp-proxy](https://github.com/sparfenyuk/mcp-proxy)** - Connect to MCP servers that run on SSE transport, or expose stdio servers as an SSE server. From 3bb87cb040ddacade3896a02260ee96b30d8f9af Mon Sep 17 00:00:00 2001 From: Prathit <67639393+Prat011@users.noreply.github.com> Date: Fri, 22 Aug 2025 13:49:22 +0530 Subject: [PATCH 05/11] docs: updated rube link in README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 81d434250c..12cc8088bc 100644 --- a/README.md +++ b/README.md @@ -367,7 +367,7 @@ Official integrations are maintained by companies building production ready MCP - Rodin **[Rodin](https://github.com/DeemosTech/rodin-api-mcp)** - Generate 3D Models with [Hyper3D Rodin](https://hyper3d.ai) - Root Signals Logo **[Root Signals](https://github.com/root-signals/root-signals-mcp)** - Improve and quality control your outputs with evaluations using LLM-as-Judge - **[Routine](https://github.com/routineco/mcp-server)** - MCP server to interact with [Routine](https://routine.co/): calendars, tasks, notes, etc. -- Composio Logo **[Rube](https://rube.composio.dev)** - Rube is a Model Context Protocol (MCP) server that connects your AI tools to 500+ apps like Gmail, Slack, GitHub, and Notion. Simply install it in your AI client, authenticate once with your apps, and start asking your AI to perform real actions like "Send an email" or "Create a task." +- Composio Logo **[Rube](https://github.com/ComposioHQ/Rube)** - Rube is a Model Context Protocol (MCP) server that connects your AI tools to 500+ apps like Gmail, Slack, GitHub, and Notion. Simply install it in your AI client, authenticate once with your apps, and start asking your AI to perform real actions like "Send an email" or "Create a task." - SafeDep Logo **[SafeDep](https://github.com/safedep/vet/blob/main/docs/mcp.md)** - SafeDep `vet-mcp` helps in vetting open source packages for security risks—such as vulnerabilities and malicious code—before they're used in your project, especially with AI-generated code suggestions. - SafeLine Logo **[SafeLine](https://github.com/chaitin/SafeLine/tree/main/mcp_server)** - [SafeLine](https://safepoint.cloud/landing/safeline) is a self-hosted WAF(Web Application Firewall) to protect your web apps from attacks and exploits. - ScrAPI Logo **[ScrAPI](https://github.com/DevEnterpriseSoftware/scrapi-mcp)** - Web scraping using [ScrAPI](https://scrapi.tech). Extract website content that is difficult to access because of bot detection, captchas or even geolocation restrictions. From ed51a7dcf950b1843c375fbb10b151e5a5432358 Mon Sep 17 00:00:00 2001 From: Nikko Gonzales <74746556+nikkoxgonzales@users.noreply.github.com> Date: Fri, 22 Aug 2025 22:37:36 +0800 Subject: [PATCH 06/11] Update README.md --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 19f5cbb8c3..d32344f175 100644 --- a/README.md +++ b/README.md @@ -581,6 +581,7 @@ A growing set of community-developed and maintained servers demonstrates various - **[context-portal](https://github.com/GreatScottyMac/context-portal)** - Context Portal (ConPort) is a memory bank database system that effectively builds a project-specific knowledge graph, capturing entities like decisions, progress, and architecture, along with their relationships. This serves as a powerful backend for Retrieval Augmented Generation (RAG), enabling AI assistants to access precise, up-to-date project information. - **[cplusplus-mcp](https://github.com/kandrwmrtn/cplusplus_mcp)** - Semantic C++ code analysis using libclang. Enables Claude to understand C++ codebases through AST parsing rather than text search - find classes, navigate inheritance, trace function calls, and explore code relationships. - **[CreateveAI Nexus](https://github.com/spgoodman/createveai-nexus-server)** - Open-Source Bridge Between AI Agents and Enterprise Systems, with simple custom API plug-in capabilities (including close compatibility with ComfyUI nodes), support for Copilot Studio's MCP agent integations, and support for Azure deployment in secure environments with secrets stored in Azure Key Vault, as well as straightforward on-premises deployment. +- **[CRASH](https://github.com/nikkoxgonzales/crash-mcp)** - MCP server for structured, iterative reasoning and thinking with flexible validation, confidence tracking, revision mechanisms, and branching support. - **[Creatify](https://github.com/TSavo/creatify-mcp)** - MCP Server that exposes Creatify AI API capabilities for AI video generation, including avatar videos, URL-to-video conversion, text-to-speech, and AI-powered editing tools. - **[Cronlytic](https://github.com/Cronlytic/cronlytic-mcp-server)** - Create CRUD operations for serverless cron jobs through [Cronlytic](https://cronlytic.com) MCP Server - **[crypto-feargreed-mcp](https://github.com/kukapay/crypto-feargreed-mcp)** - Providing real-time and historical Crypto Fear & Greed Index data. From cf4ffdb0bfdfe17e40ed57de62de1442d72b9949 Mon Sep 17 00:00:00 2001 From: Cora 7 Date: Sat, 23 Aug 2025 00:49:53 +1000 Subject: [PATCH 07/11] Update Voice MCP to Voice Mode Voice MCP has been renamed to Voice Mode. This updates: - Name from 'Voice MCP' to 'Voice Mode' - GitHub URL from voice-mcp to voicemode - Website from voice-mcp.com to voicemode.ai --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 19f5cbb8c3..54e778ac0d 100644 --- a/README.md +++ b/README.md @@ -1162,7 +1162,7 @@ A growing set of community-developed and maintained servers demonstrates various - **[Video Still Capture](https://github.com/13rac1/videocapture-mcp)** - 📷 Capture video stills from an OpenCV-compatible webcam or other video source. - **[Virtual location (Google Street View,etc.)](https://github.com/mfukushim/map-traveler-mcp)** - Integrates Google Map, Google Street View, PixAI, Stability.ai, ComfyUI API and Bluesky to provide a virtual location simulation in LLM (written in Effect.ts) - **[VMware Fusion](https://github.com/yeahdongcn/vmware-fusion-mcp-server)** - Manage VMware Fusion virtual machines via the Fusion REST API. -- **[Voice MCP](https://github.com/mbailey/voice-mcp)** - Enable voice conversations with Claude using any OpenAI-compatible STT/TTS service ([voice-mcp.com](https://voice-mcp.com)) +- **[Voice Mode](https://github.com/mbailey/voicemode)** - Enable voice conversations with Claude using any OpenAI-compatible STT/TTS service ([voicemode.ai](https://voicemode.ai)) - **[Voice Status Report](https://github.com/tomekkorbak/voice-status-report-mcp-server)** - An MCP server that provides voice status updates using OpenAI's text-to-speech API, to be used with Cursor or Claude Code. - **[VolcEngine TOS](https://github.com/dinghuazhou/sample-mcp-server-tos)** - A sample MCP server for VolcEngine TOS that flexibly get objects from TOS. - **[Voyp](https://github.com/paulotaylor/voyp-mcp)** - VOYP MCP server for making calls using Artificial Intelligence. From 1aee44a951da48878cc929a75ee9c1bf6b7a5773 Mon Sep 17 00:00:00 2001 From: isnow890 <53589758+isnow890@users.noreply.github.com> Date: Sat, 23 Aug 2025 00:20:39 +0900 Subject: [PATCH 08/11] feat: add Data4Library MCP server to the readme --- README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/README.md b/README.md index 19f5cbb8c3..db37e39007 100644 --- a/README.md +++ b/README.md @@ -599,6 +599,8 @@ A growing set of community-developed and maintained servers demonstrates various - **[Datadog](https://github.com/GeLi2001/datadog-mcp-server)** - Datadog MCP Server for application tracing, monitoring, dashboard, incidents queries built on official datadog api. - **[Dataset Viewer](https://github.com/privetin/dataset-viewer)** - Browse and analyze Hugging Face datasets with features like search, filtering, statistics, and data export - **[DataWorks](https://github.com/aliyun/alibabacloud-dataworks-mcp-server)** - A Model Context Protocol (MCP) server that provides tools for AI, allowing it to interact with the [DataWorks](https://www.alibabacloud.com/help/en/dataworks/) Open API through a standardized interface. This implementation is based on the Alibaba Cloud Open API and enables AI agents to perform cloud resources operations seamlessly. +- **[Data4library](https://github.com/isnow890/data4library-mcp)** (by isnow890) - MCP server for Korea's Library Information Naru API, providing comprehensive access to public library data, book searches, loan status, reading statistics, and GPS-based nearby library discovery across South Korea. + - **[DaVinci Resolve](https://github.com/samuelgursky/davinci-resolve-mcp)** - MCP server integration for DaVinci Resolve providing powerful tools for video editing, color grading, media management, and project control. - **[DBHub](https://github.com/bytebase/dbhub/)** - Universal database MCP server connecting to MySQL, MariaDB, PostgreSQL, and SQL Server. - **[Deebo](https://github.com/snagasuri/deebo-prototype)** – Agentic debugging MCP server that helps AI coding agents delegate and fix hard bugs through isolated multi-agent hypothesis testing. From d381cf1ffda963ccd04b9a5a1913595163d8bcf8 Mon Sep 17 00:00:00 2001 From: Enrico Ballardini Date: Sat, 23 Aug 2025 08:19:01 +0200 Subject: [PATCH 09/11] feat(directory_tree): add excludePatterns support & documentation (#623) - Update documentation with directory_tree declaration - Add excludePatterns parameter to DirectoryTreeArgsSchema - Implement pattern exclusion in buildTree function using minimatch - Pass excludePatterns through recursive calls - Support both simple and glob patterns for exclusion - Maintain consistent behavior with search_files implementation * Add tests and fix implementation --------- Co-authored-by: Ola Hungerford Co-authored-by: Adam Jones Co-authored-by: Adam Jones --- src/filesystem/README.md | 13 ++ .../__tests__/directory-tree.test.ts | 147 ++++++++++++++++++ src/filesystem/index.ts | 23 ++- 3 files changed, 180 insertions(+), 3 deletions(-) create mode 100644 src/filesystem/__tests__/directory-tree.test.ts diff --git a/src/filesystem/README.md b/src/filesystem/README.md index 0f456f3cd2..ccef2d6708 100644 --- a/src/filesystem/README.md +++ b/src/filesystem/README.md @@ -153,6 +153,19 @@ The server's directory access control follows this flow: - Case-insensitive matching - Returns full paths to matches +- **directory_tree** + - Get recursive JSON tree structure of directory contents + - Inputs: + - `path` (string): Starting directory + - `excludePatterns` (string[]): Exclude any patterns. Glob formats are supported. + - Returns: + - JSON array where each entry contains: + - `name` (string): File/directory name + - `type` ('file'|'directory'): Entry type + - `children` (array): Present only for directories + - Empty array for empty directories + - Omitted for files + - **get_file_info** - Get detailed file/directory metadata - Input: `path` (string) diff --git a/src/filesystem/__tests__/directory-tree.test.ts b/src/filesystem/__tests__/directory-tree.test.ts new file mode 100644 index 0000000000..6828650cc0 --- /dev/null +++ b/src/filesystem/__tests__/directory-tree.test.ts @@ -0,0 +1,147 @@ +import { describe, it, expect, beforeEach, afterEach } from '@jest/globals'; +import * as fs from 'fs/promises'; +import * as path from 'path'; +import * as os from 'os'; + +// We need to test the buildTree function, but it's defined inside the request handler +// So we'll extract the core logic into a testable function +import { minimatch } from 'minimatch'; + +interface TreeEntry { + name: string; + type: 'file' | 'directory'; + children?: TreeEntry[]; +} + +async function buildTreeForTesting(currentPath: string, rootPath: string, excludePatterns: string[] = []): Promise { + const entries = await fs.readdir(currentPath, {withFileTypes: true}); + const result: TreeEntry[] = []; + + for (const entry of entries) { + const relativePath = path.relative(rootPath, path.join(currentPath, entry.name)); + const shouldExclude = excludePatterns.some(pattern => { + if (pattern.includes('*')) { + return minimatch(relativePath, pattern, {dot: true}); + } + // For files: match exact name or as part of path + // For directories: match as directory path + return minimatch(relativePath, pattern, {dot: true}) || + minimatch(relativePath, `**/${pattern}`, {dot: true}) || + minimatch(relativePath, `**/${pattern}/**`, {dot: true}); + }); + if (shouldExclude) + continue; + + const entryData: TreeEntry = { + name: entry.name, + type: entry.isDirectory() ? 'directory' : 'file' + }; + + if (entry.isDirectory()) { + const subPath = path.join(currentPath, entry.name); + entryData.children = await buildTreeForTesting(subPath, rootPath, excludePatterns); + } + + result.push(entryData); + } + + return result; +} + +describe('buildTree exclude patterns', () => { + let testDir: string; + + beforeEach(async () => { + testDir = await fs.mkdtemp(path.join(os.tmpdir(), 'filesystem-test-')); + + // Create test directory structure + await fs.mkdir(path.join(testDir, 'src')); + await fs.mkdir(path.join(testDir, 'node_modules')); + await fs.mkdir(path.join(testDir, '.git')); + await fs.mkdir(path.join(testDir, 'nested', 'node_modules'), { recursive: true }); + + // Create test files + await fs.writeFile(path.join(testDir, '.env'), 'SECRET=value'); + await fs.writeFile(path.join(testDir, '.env.local'), 'LOCAL_SECRET=value'); + await fs.writeFile(path.join(testDir, 'src', 'index.js'), 'console.log("hello");'); + await fs.writeFile(path.join(testDir, 'package.json'), '{}'); + await fs.writeFile(path.join(testDir, 'node_modules', 'module.js'), 'module.exports = {};'); + await fs.writeFile(path.join(testDir, 'nested', 'node_modules', 'deep.js'), 'module.exports = {};'); + }); + + afterEach(async () => { + await fs.rm(testDir, { recursive: true, force: true }); + }); + + it('should exclude files matching simple patterns', async () => { + // Test the current implementation - this will fail until the bug is fixed + const tree = await buildTreeForTesting(testDir, testDir, ['.env']); + const fileNames = tree.map(entry => entry.name); + + expect(fileNames).not.toContain('.env'); + expect(fileNames).toContain('.env.local'); // Should not exclude this + expect(fileNames).toContain('src'); + expect(fileNames).toContain('package.json'); + }); + + it('should exclude directories matching simple patterns', async () => { + const tree = await buildTreeForTesting(testDir, testDir, ['node_modules']); + const dirNames = tree.map(entry => entry.name); + + expect(dirNames).not.toContain('node_modules'); + expect(dirNames).toContain('src'); + expect(dirNames).toContain('.git'); + }); + + it('should exclude nested directories with same pattern', async () => { + const tree = await buildTreeForTesting(testDir, testDir, ['node_modules']); + + // Find the nested directory + const nestedDir = tree.find(entry => entry.name === 'nested'); + expect(nestedDir).toBeDefined(); + expect(nestedDir!.children).toBeDefined(); + + // The nested/node_modules should also be excluded + const nestedChildren = nestedDir!.children!.map(child => child.name); + expect(nestedChildren).not.toContain('node_modules'); + }); + + it('should handle glob patterns correctly', async () => { + const tree = await buildTreeForTesting(testDir, testDir, ['*.env']); + const fileNames = tree.map(entry => entry.name); + + expect(fileNames).not.toContain('.env'); + expect(fileNames).toContain('.env.local'); // *.env should not match .env.local + expect(fileNames).toContain('src'); + }); + + it('should handle dot files correctly', async () => { + const tree = await buildTreeForTesting(testDir, testDir, ['.git']); + const dirNames = tree.map(entry => entry.name); + + expect(dirNames).not.toContain('.git'); + expect(dirNames).toContain('.env'); // Should not exclude this + }); + + it('should work with multiple exclude patterns', async () => { + const tree = await buildTreeForTesting(testDir, testDir, ['node_modules', '.env', '.git']); + const entryNames = tree.map(entry => entry.name); + + expect(entryNames).not.toContain('node_modules'); + expect(entryNames).not.toContain('.env'); + expect(entryNames).not.toContain('.git'); + expect(entryNames).toContain('src'); + expect(entryNames).toContain('package.json'); + }); + + it('should handle empty exclude patterns', async () => { + const tree = await buildTreeForTesting(testDir, testDir, []); + const entryNames = tree.map(entry => entry.name); + + // All entries should be included + expect(entryNames).toContain('node_modules'); + expect(entryNames).toContain('.env'); + expect(entryNames).toContain('.git'); + expect(entryNames).toContain('src'); + }); +}); \ No newline at end of file diff --git a/src/filesystem/index.ts b/src/filesystem/index.ts index 310cfa6bba..ee4307c474 100644 --- a/src/filesystem/index.ts +++ b/src/filesystem/index.ts @@ -14,6 +14,7 @@ import { createReadStream } from "fs"; import path from "path"; import { z } from "zod"; import { zodToJsonSchema } from "zod-to-json-schema"; +import { minimatch } from "minimatch"; import { normalizePath, expandHome } from './path-utils.js'; import { getValidRootDirectories } from './roots-utils.js'; import { @@ -121,6 +122,7 @@ const ListDirectoryWithSizesArgsSchema = z.object({ const DirectoryTreeArgsSchema = z.object({ path: z.string(), + excludePatterns: z.array(z.string()).optional().default([]) }); const MoveFileArgsSchema = z.object({ @@ -528,13 +530,28 @@ server.setRequestHandler(CallToolRequestSchema, async (request) => { type: 'file' | 'directory'; children?: TreeEntry[]; } + const rootPath = parsed.data.path; - async function buildTree(currentPath: string): Promise { + async function buildTree(currentPath: string, excludePatterns: string[] = []): Promise { const validPath = await validatePath(currentPath); const entries = await fs.readdir(validPath, {withFileTypes: true}); const result: TreeEntry[] = []; for (const entry of entries) { + const relativePath = path.relative(rootPath, path.join(currentPath, entry.name)); + const shouldExclude = excludePatterns.some(pattern => { + if (pattern.includes('*')) { + return minimatch(relativePath, pattern, {dot: true}); + } + // For files: match exact name or as part of path + // For directories: match as directory path + return minimatch(relativePath, pattern, {dot: true}) || + minimatch(relativePath, `**/${pattern}`, {dot: true}) || + minimatch(relativePath, `**/${pattern}/**`, {dot: true}); + }); + if (shouldExclude) + continue; + const entryData: TreeEntry = { name: entry.name, type: entry.isDirectory() ? 'directory' : 'file' @@ -542,7 +559,7 @@ server.setRequestHandler(CallToolRequestSchema, async (request) => { if (entry.isDirectory()) { const subPath = path.join(currentPath, entry.name); - entryData.children = await buildTree(subPath); + entryData.children = await buildTree(subPath, excludePatterns); } result.push(entryData); @@ -551,7 +568,7 @@ server.setRequestHandler(CallToolRequestSchema, async (request) => { return result; } - const treeData = await buildTree(parsed.data.path); + const treeData = await buildTree(rootPath, parsed.data.excludePatterns); return { content: [{ type: "text", From fd886fac9c40c579eaffde7a00f13fa769731bfc Mon Sep 17 00:00:00 2001 From: Finn Andersen Date: Sat, 23 Aug 2025 09:37:53 +0300 Subject: [PATCH 10/11] Support glob `pattern` in search_files tool (#745) Co-authored-by: Adam Jones Co-authored-by: Claude Co-authored-by: Adam Jones --- src/filesystem/README.md | 6 +++--- src/filesystem/__tests__/lib.test.ts | 6 +++--- src/filesystem/index.ts | 6 +++--- src/filesystem/lib.ts | 10 +++++----- 4 files changed, 14 insertions(+), 14 deletions(-) diff --git a/src/filesystem/README.md b/src/filesystem/README.md index ccef2d6708..499fca5ad6 100644 --- a/src/filesystem/README.md +++ b/src/filesystem/README.md @@ -145,12 +145,12 @@ The server's directory access control follows this flow: - Fails if destination exists - **search_files** - - Recursively search for files/directories + - Recursively search for files/directories that match or do not match patterns - Inputs: - `path` (string): Starting directory - `pattern` (string): Search pattern - - `excludePatterns` (string[]): Exclude any patterns. Glob formats are supported. - - Case-insensitive matching + - `excludePatterns` (string[]): Exclude any patterns. + - Glob-style pattern matching - Returns full paths to matches - **directory_tree** diff --git a/src/filesystem/__tests__/lib.test.ts b/src/filesystem/__tests__/lib.test.ts index 76d3679280..cc13ef0353 100644 --- a/src/filesystem/__tests__/lib.test.ts +++ b/src/filesystem/__tests__/lib.test.ts @@ -316,7 +316,7 @@ describe('Lib Functions', () => { const result = await searchFilesWithValidation( testDir, - 'test', + '*test*', allowedDirs, { excludePatterns: ['*.log', 'node_modules'] } ); @@ -346,7 +346,7 @@ describe('Lib Functions', () => { const result = await searchFilesWithValidation( testDir, - 'test', + '*test*', allowedDirs, {} ); @@ -370,7 +370,7 @@ describe('Lib Functions', () => { const result = await searchFilesWithValidation( testDir, - 'test', + '*test*', allowedDirs, { excludePatterns: ['*.backup'] } ); diff --git a/src/filesystem/index.ts b/src/filesystem/index.ts index ee4307c474..d732c4d2a6 100644 --- a/src/filesystem/index.ts +++ b/src/filesystem/index.ts @@ -277,9 +277,9 @@ server.setRequestHandler(ListToolsRequestSchema, async () => { name: "search_files", description: "Recursively search for files and directories matching a pattern. " + - "Searches through all subdirectories from the starting path. The search " + - "is case-insensitive and matches partial names. Returns full paths to all " + - "matching items. Great for finding files when you don't know their exact location. " + + "The patterns should be glob-style patterns that match paths relative to the working directory. " + + "Use pattern like '*.ext' to match files in current directory, and '**/*.ext' to match files in all subdirectories. " + + "Returns full paths to all matching items. Great for finding files when you don't know their exact location. " + "Only searches within allowed directories.", inputSchema: zodToJsonSchema(SearchFilesArgsSchema) as ToolInput, }, diff --git a/src/filesystem/lib.ts b/src/filesystem/lib.ts index 40cb316e53..240ca0d476 100644 --- a/src/filesystem/lib.ts +++ b/src/filesystem/lib.ts @@ -367,14 +367,14 @@ export async function searchFilesWithValidation( await validatePath(fullPath); const relativePath = path.relative(rootPath, fullPath); - const shouldExclude = excludePatterns.some(excludePattern => { - const globPattern = excludePattern.includes('*') ? excludePattern : `**/${excludePattern}/**`; - return minimatch(relativePath, globPattern, { dot: true }); - }); + const shouldExclude = excludePatterns.some(excludePattern => + minimatch(relativePath, excludePattern, { dot: true }) + ); if (shouldExclude) continue; - if (entry.name.toLowerCase().includes(pattern.toLowerCase())) { + // Use glob matching for the search pattern + if (minimatch(relativePath, pattern, { dot: true })) { results.push(fullPath); } From 2a4b7b0649734b75faf85f11c80277ddc31d2348 Mon Sep 17 00:00:00 2001 From: Juliette Sivan <91728573+juliette0704@users.noreply.github.com> Date: Sat, 23 Aug 2025 09:29:17 +0200 Subject: [PATCH 11/11] feat(readme): add Linkup MCP server to the list of offical integrations (#2575) Co-authored-by: Adam Jones --- README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/README.md b/README.md index e230c714ca..f466376057 100644 --- a/README.md +++ b/README.md @@ -259,6 +259,8 @@ Official integrations are maintained by companies building production ready MCP - Linear Logo **[Linear](https://linear.app/docs/mcp)** - Search, create, and update Linear issues, projects, and comments. - Lingo.dev Logo **[Lingo.dev](https://github.com/lingodotdev/lingo.dev/blob/main/mcp.md)** - Make your AI agent speak every language on the planet, using [Lingo.dev](https://lingo.dev) Localization Engine. - LiGo Logo **[LinkedIn MCP Runner](https://github.com/ertiqah/linkedin-mcp-runner)** - Write, edit, and schedule LinkedIn posts right from ChatGPT and Claude with [LiGo](https://ligo.ertiqah.com/). +- Linkup Logo **[Linkup](https://github.com/LinkupPlatform/js-mcp-server)** - (JS version) MCP server that provides web search capabilities through Linkup's advanced search API. This server enables AI assistants and development tools to perform intelligent web searches with natural language queries. +- Linkup Logo **[Linkup](https://github.com/LinkupPlatform/python-mcp-server)** - (Python version) MCP server that provides web search capabilities through Linkup's advanced search API. This server enables AI assistants and development tools to perform intelligent web searches with natural language queries. - Lisply **[Lisply](https://github.com/gornskew/lisply-mcp)** - Flexible frontend for compliant Lisp-speaking backends. - Litmus.io Logo **[Litmus.io](https://github.com/litmusautomation/litmus-mcp-server)** - Official MCP server for configuring [Litmus](https://litmus.io) Edge for Industrial Data Collection, Edge Analytics & Industrial AI. - Liveblocks Logo **[Liveblocks](https://github.com/liveblocks/liveblocks-mcp-server)** - Ready‑made features for AI & human collaboration—use this to develop your [Liveblocks](https://liveblocks.io) app quicker.