Discover 518 MCPs built for GitHub.
Enables advanced automation and interaction capabilities with GitHub APIs for developers and tools using the Model Context Protocol.
Provides accurate, hallucination-free answers by leveraging diverse knowledge sources and integrating with large language models.
Converts Git repository URLs into prompt-friendly text extracts of codebases for large language models.
Transforms GitHub repositories and local code into beginner-friendly tutorials by leveraging artificial intelligence.
Provides an AI-powered conversational search engine for codebases, enabling natural language queries, code navigation, and patch generation.
Transforms any GitHub project into a documentation hub accessible to AI tools, preventing hallucinations by providing accurate and up-to-date context.
Enhances AI coding agents by providing semantic code search and deep context from an entire codebase.
Provides containerized development environments, enabling multiple coding agents to work safely and independently with diverse tech stacks.
Programmatically assembles prompts for LLMs using JavaScript to orchestrate LLMs, tools, and data in code.
Index and search code across multiple repositories and branches from various code hosting platforms.
Streamlines AI coding agents' workflow for planning and executing software development tasks effectively.
Unify access to diverse data sources, from files and databases to popular applications, by querying them with SQL and integrating with large language models.
Automates AI-powered workflows directly within your codebase.
Enables rapid, trigram-based text search capabilities specifically for source code repositories.
Connects local LLMs (via Ollama) to Model Context Protocol (MCP) servers, allowing open-source models to use external tools.
Collects and shares AI prompts, best practices, and curated rules to enhance developer workflows within AI-assisted coding tools.
Builds a project-specific knowledge graph to supercharge AI assistants with context-aware Retrieval Augmented Generation (RAG) capabilities.
Enables coding agents to communicate and coordinate asynchronously, providing a mail-like system with identities, inboxes, and shared context.
Enforces Protocol Buffer style and conventions through linting and automated fixes.
Empowers AI assistants to act as a personal chef, recommending recipes and planning meals based on a comprehensive cooking guide.
Scroll for more results...