URL-based MCP server creation
Create a remote MCP server for a GitHub project by replacing `github.com` with `gitmcp.io` in the repository URL.
GitMCP creates a remote Model Context Protocol (MCP) server for public GitHub repositories and GitHub Pages sites. It helps MCP-compatible AI assistants access repository documentation and code context for more relevant coding responses.
GitMCP creates a remote Model Context Protocol (MCP) server for a public GitHub repository or GitHub Pages site. Users create a project-specific server URL by replacing the relevant GitHub domain with gitmcp.io, then connect that URL to an MCP-compatible AI assistant.
The connected assistant can use repository context—including files such as llms.txt, llms-full.txt, and readme.md—to provide responses grounded in the selected project. GitMCP is intended for AI-assisted coding and documentation workflows where project-specific context is more useful than a general-purpose conversation.
Create a remote MCP server for a GitHub project by replacing `github.com` with `gitmcp.io` in the repository URL.
GitMCP also supports GitHub Pages URLs, allowing published project documentation to be connected as MCP context.
The service reads available project materials such as `llms.txt`, `llms-full.txt`, `readme.md`, and other repository content for use by connected AI assistants.
The documented workflow starts with a GitMCP URL and does not require users to build or deploy an MCP server for each public repository.
The site includes setup examples for Claude, Cursor, Windsurf, VSCode, Cline, Highlight AI, Augment Code, and Msty AI.
Connect a repository to an AI assistant so coding questions can be answered using the project’s available files and documentation.
Use a GitHub Pages site or repository documentation as context when learning how a public project is structured or used.
Give an MCP-compatible coding tool project-specific context before requesting implementation guidance, explanations, or repository-related help.
Reuse the GitMCP server URL across supported assistants by following the configuration format provided for each tool.
GitMCP creates a remote Model Context Protocol server for a GitHub project. The server URL can be added to an MCP-compatible AI assistant.
For a GitHub repository, replace the `github.com` portion of its URL with `gitmcp.io`. GitHub Pages URLs can be converted in the same general way by using the GitMCP domain.
The site states that GitMCP works with public GitHub repositories and GitHub Pages. The available source does not confirm support for private repositories or other hosting platforms.
The site lists Claude, Cursor, Windsurf, VSCode, Cline, Highlight AI, Augment Code, and Msty AI, and provides configuration examples for connecting the server URL.
GitMCP can provide repository context including `llms.txt`, `llms-full.txt`, `readme.md`, and other available project content. The source does not specify a complete file inventory or additional processing limits.
modelcontextprotocol.io
The official TypeScript SDK for building Model Context Protocol servers and clients. It provides a repository-organized foundation for MCP development, with separate client, server, core, middleware, documentation, and example areas.
0mcp.io
0mcp converts selected operations from an OpenAPI-described API into a hosted Model Context Protocol (MCP) server. It helps SaaS, platform, and internal teams make approved API actions available to MCP-compatible AI clients without implementing and operating the protocol layer themselves.
glama.ai
Glama is a registry and infrastructure platform for discovering, evaluating, and connecting to Model Context Protocol (MCP) servers, connectors, clients, and tools. It supports browsing open-source and remote MCP entries, with hosted access and gateway features described on the site.
dspy.ai
DSPy is an open-source framework for programming language-model applications instead of manually prompting them. Its public repository provides the project code, documentation, tests, issue tracking, and contribution workflow.
deepaksinghcs14.github.io
deadeye is a plugin for coding agents that selects a suitable model and effort level for each task, while trimming verbose command output before it enters context. It is built for Claude Code and also supports Codex CLI, Gemini CLI, Cursor, and Windsurf on an experimental basis.
app.dezycro.ai
Dezycro is an operations layer for AI coding agents that provides product context, steers work, verifies behavior against requirements, and records decisions. It is designed for developers, product teams, and organizations that want to use agents without giving Dezycro access to source code.