#mcp-server

Arbor v2.4.0 is a code graph MCP server that helps AI agents navigate codebases structurally instead of using grep. It provides a semantic understanding of code relationships for more efficient agent-based code analysis.

FEOM is a new Windows GUI automation tool that achieves 8ms response times without requiring a GPU. It enables fast, lightweight automation of native Windows interfaces for developers and testers.

Vublox Agent Tools is an MCP server offering six tools for AI agents to access live football scores, match summaries, player info, and recent results. It requires no API key or signup, running simply via npx.

The article introduces an MCP (Model Context Protocol) server built for the Universal Commerce Protocol (UCP), enabling AI agents to interact with commerce data and actions in a standardized way.

Scopewalker is an open-source MCP server that gives AI agents eight read-only tools for codebase complexity metrics—line counts, cognitive complexity, parameter counts, doc coverage, code smells, and more. It supports TS/JS, Python, Go, Rust, Java, C/C++, and Ruby, runs locally over stdio with no network calls.

Apple has introduced the Safari MCP (Model Context Protocol) server for web developers, enabling seamless integration between AI-powered tools and the Safari Web Inspector. The server allows developers to use natural language to inspect, debug, and analyze web pages in Safari, leveraging Web Inspector protocols to interact with live browser sessions.

Enola is an open-source architecture engine that indexes codebases into a deterministic knowledge graph, exposing an MCP server. It enables impact analysis, dead code discovery, and dependency analysis across multiple repositories without using an LLM for graph construction. The tool aims to help developers and AI agents understand large, distributed codebases more efficiently.

The article presents four key rules for building efficient Model Context Protocol (MCP) servers, arguing developers should design them like user interfaces rather than traditional APIs. It emphasizes clear, purpose-driven tools, intuitive naming, consistent error handling, and thoughtful resource organization to improve client interactions and overall usability.

Tidesman is a native MCP server designed to support Apple Container's Linux container workflows, providing integration for container management on Apple systems.

Apple has introduced the Safari MCP server, a tool that allows web developers to integrate Safari’s Web Inspector capabilities with MCP-compatible AI assistants and automation tools. It enables tasks such as evaluating JavaScript, inspecting elements, managing network requests, and taking screenshots of live web pages, aiming to streamline debugging and testing workflows.

Pitwall is an MCP (Model Context Protocol) server that provides access to Formula 1 data, including real-time race information, standings, team and driver details, and historical race results.

The article discusses the design of a Model Context Protocol (MCP) server tailored for unstructured data, outlining the architecture and considerations for enabling AI models to interact with non-relational data sources through standardized interfaces.

The article describes how to set up a local MCP (Model Context Protocol) server on an iPhone to connect Apple Health and Workout data with Anthropic's Codex assistant, enabling automated workout planning and analysis based on personal fitness history.

BullRun is a free global stock screener that includes an MCP (Model Context Protocol) server, allowing users to filter and analyze stocks across global markets without cost.

League Loom is an MCP (Model Context Protocol) server that connects fantasy sports platforms like ESPN, Sleeper, and Fantrax with AI assistants like ChatGPT and Claude. It allows users to access and manage their fantasy sports leagues directly through conversational AI interfaces.

System1, the company behind Dogpile.com, has rebuilt its backend as a metered search API and MCP server designed for AI agents, offering structured JSON output, result scraping, and deep research modes. The service is currently single-source but plans to add multi-source aggregation to address the problem that different search engines return different results for the same query.

Hail.so is an open-source MCP server, CLI, and API unifying email, SMS, and phone calls via Twilio, AWS SES, LiveKit, and LLM providers. It simplifies multi-provider setup and billing, built from a year of production AI voicebot work.

This page introduces a GraphQL MCP server and associated GraphiQL plugins, designed to enhance GraphQL development workflows by integrating MCP capabilities directly into the GraphiQL IDE.

Tsar-MCP is a learning guide for creating an MCP (Model Context Protocol) server in C/C++ with no external dependencies. It covers I/O flow, JSON parsing (using a decade-old JSON parser), and request dispatch, and provides an asynchronous, enterprise-ready baseline for building custom MCP servers.

A comprehensive MCP server has been created that exposes the full WhatsApp Business API through the PyWA library, enabling integration of WhatsApp messaging capabilities into AI applications.

The page introduces a Model Context Protocol (MCP) server that supports mainstream eBook formats such as ePub and PDF, enabling AI assistants to read and process digital books.

A UK meat price comparison site that scrapes data from multiple online butchers has added an MCP server, allowing users to query price history, basket comparisons, and deals via AI tools like Claude and ChatGPT instead of using the website's UI. The service is read-only, free, and requires an email registration for an API key.

Forensic-deepdive is a tool that creates a code knowledge graph and provides an MCP (Model Context Protocol) server for AI agents, enabling them to better understand and navigate codebases.

Java MCP server supporting Streamable HTTP and Netty transports, designed for stateless deployment.

The article argues that every app that stores user data should ship a built-in MCP (Model Context Protocol) server, allowing AI tools to directly query and interact with that data. The author suggests a pattern of implementing MCP server functionality early in development and provides examples of how to add capabilities like tools, resources, and prompts.

A new SQL MCP Server called DataBridge has been posted on GitHub, achieving a 61.37% score on the DataAgentBench leaderboard when paired with the GLM 5.2 model.

A developer built an MCP server that indexes all repositories in a codebase, enables natural language and dependency-based search, and automates batch changes (like updating a library across repos) by creating PRs and monitoring workflows. The tool uses MongoDB, Redis, and AI agents to simplify maintaining consistency across many microservices.

AnswerJournal is an MCP server with seven tools that allows users to save and share AI answers from conversations. Answers can be set as public or private and are stored on a personal feed accessible through MCP-compatible AI interfaces.

The video demonstrates an MCP (Model Context Protocol) server that provides AI agents with practical coding tools, showing how they can interact with real development environments to perform tasks like editing files and running commands.

The article describes the process of shipping a remote MCP (Model Context Protocol) server with OAuth protection, covering both the specification's implementation and three security bugs discovered during development.