WebMCP is a project that allows websites to support client-side LLMs (Large Language Models). It enables the sharing of tools, resources, and prompts between websites and LLMs through a local WebSocket server without the need for API keys and supports multiple models.

Pincer-MCP is a security-hardened MCP gateway that protects the API keys of AI agents through a proxy token architecture, ensuring that agents can only use proxy tokens and cannot access real keys. It supports various AI services and GPG signing tools.

Janee is an AI agent key management tool based on the MCP protocol. It securely stores and injects API keys as an intermediary, enabling agents to call services without touching the original keys. It also provides complete audit logs, access policy control, and session management functions.

The Infisical Model Context Protocol (MCP) is a service protocol that integrates with the Infisical API through function calls. It supports multiple tool operations such as creating, deleting, and updating keys, and provides a debugging tool called MCP Inspector.

Jarvis MCP is a browser-based voice conversation tool that allows users to have natural voice conversations with AI assistants through a microphone. It supports voice recognition in more than 30 languages and remote access, and no additional software or API keys are required for installation.

The AWS Service Reference MCP Server provides a tool for querying AWS services, API operations, condition keys, and resource types.

An intelligent service for automatically discovering and configuring MCP servers. It eliminates the need for manual setup commands and API keys, enabling automatic selection and configuration of MCP servers through a single configuration file.

This project is a quick - start template for a remote MCP server based on Azure Functions and Python. It supports communication via HTTPS and secure keys and integrates the Booking COM travel API to implement attraction query and review functions.

Fastly MCP is a tool that integrates Fastly API features into an AI assistant through the Model Context Protocol (MCP), allowing users to manage CDN services, caching, security configurations, etc. via AI while protecting the security of API keys.

Fastly MCP is a tool that integrates Fastly API features into AI assistants through the Model Context Protocol (MCP), allowing users to manage CDN services, caches, security configurations, etc. through natural language instructions while ensuring the security of API keys.

Fetch Browser is a powerful headless browser MCP server designed for AI agents, which can obtain web page content and perform Google searches without API keys. It supports multiple content format conversions and intelligent error handling.

A privacy - first document search server that runs entirely locally, providing semantic search functions for AI programming tools through the MCP protocol. No API keys or cloud services are required, and all data processing is completed on the user's computer.

The Infisical Model Context Protocol (MCP) Server provides a set of tools for integrating with the Infisical API through function calls, supporting operations such as creating, deleting, updating, and querying keys. It is suitable for key management and project collaboration.

A security tool that prevents API keys from being accidentally committed to the Git repository by loading keys from a configuration file in the user's home directory and injecting them into the MCP service environment.

This project uses the MCP Python SDK to build a multifunctional server, providing note management, weather query, and news search functions, and supports configuring API keys through the .env file.

BlockRun MCP is an AI model aggregation service designed for Claude Code. It provides unified access to over 30 AI models without the need to manage multiple API keys. Payments are made on-demand using a single USDC wallet.

The Gentoro MCP server supports the Gentoro service, enabling Claude to interact with the Gentoro bridge and its underlying functions. Users can create and manage tool bridges through their Gentoro accounts and integrate them into agents such as Claude via API keys.

An MCP server based on FastAPI, deployed in Azure Container Apps, providing SSE interfaces for weather-related tools (such as alerts and forecasts) and authenticated via API keys.

og-mcp is an MCP server that provides AI agents with all the functions of the OpenGraph.io API, including web page metadata extraction, content scraping, screenshot, and AI image generation, and allows secure access through the standard MCP interface without exposing API keys.

This project has configured GitHub Actions workflows for testing Plane.so API endpoints, including unit tests and integration tests. You need to configure API keys and the workspace slug as keys.

Autonomous Lab is an MCP server that can transform any senior - novice workflow into an autonomous loop. AI agents play different roles (such as PI and trainee) in a design - execute - review loop, while humans act as decision - making editors. No additional API keys are required, and it can run using existing coding tool subscriptions. It supports multi - agent mode, skill container configuration, and 24 - hour continuous sessions.

A Resend email service MCP server based on the Model Context Protocol, providing AI assistants with complete Resend API functions such as sending emails, managing domains, API keys, contacts, and audiences.

This project is the code and data repository of MCP DrugBot, aiming to achieve more streamlined and intelligent drug information processing. It requires the configuration of NCBI and OpenAI API keys to run.

This project is an MCP server that provides two main functions: asynchronous task processing and dynamic addition of ReAct agent tools. Users need to configure environment variables and API keys and select different functional modules for testing by modifying the configuration file.

The MemData MCP server provides long-term memory storage and retrieval functions for AI assistants across sessions, supporting usage through API keys or wallet payments, and achieving semantic memory management.

Agent-Skill-Kit is a local-first skill framework designed for AI agents. It does not require API keys or registration and provides localized skills for agents such as Claude and Copilot through the MCP protocol, including code visualization, technology information acquisition, skill generation, and other functions.

This is a generative AI course project for beginners, providing a complete learning path from environment setup to practical application. The project includes 6 concept courses and 6 programming courses, using the Azure OpenAI service for practical operations. Learners can quickly start through GitHub Codespaces or choose to install the Python environment locally. The project emphasizes the secure management of API keys and provides detailed setup guides. In addition, learners are encouraged to participate in open-source contributions, and an AI community communication platform is provided.

The OpenAI MCP server is a tool service for managing OpenAI API keys and expenditures, supporting multiple installation methods and providing debugging functions.

The EDINET DATA MCP Server, a Docker container service providing free API keys

A server based on the Model Context Protocol (MCP) for performing enrichment queries on provided observables (such as IP addresses, domain names, etc.) through third - party services (such as VirusTotal, HybridAnalysis, etc.). This project is currently only for development and testing, supports multiple observable types and third - party services, and uses environment variables to manage API keys for security.