MCP Servers

This server lets AI assistants read and query Markdown notes from local directories, enabling lightweight knowledge base access and semantic document search. It’s designed to work well with Obsidian-style content structures and is optimized for fast search and indexing.

MCP-Obsidian enables LLMs to read, search, update, and manage Markdown files within an Obsidian vault. It supports note retrieval, file editing, block insertion, deletion, and search capabilities — making it a powerful knowledge assistant interface for personal note systems.

Serena enhances LLMs by providing essential tools for semantic code retrieval and editing. It integrates with existing LLMs, enabling them to perform coding tasks directly within your codebase. Serena supports multiple programming languages through the Language Server Protocol (LSP), including Python, Java, and TypeScript. It can be integrated with LLMs via the Model Context Protocol (MCP) or used with Agno, a model-agnostic agent framework.

Cloudflare Workers MCP provides both CLI tooling and in-Worker logic to connect AI assistants, like Claude Desktop, to Cloudflare Workers. It allows developers to expose functions or APIs from their applications or services within Cloudflare's developer platform to large language models (LLMs) in coding agents. The package translates TypeScript methods of a Worker into MCP tools that a local Node.js server can expose to MCP clients.

GitMCP lets AI assistants access any public GitHub repo’s docs and code structure instantly. No setup required — just point to a repo URL. Semantic search is built-in for efficient querying with minimal tokens. No telemetry, no tracking.

Fetcher MCP leverages Playwright to execute JavaScript, allowing it to handle dynamic web content effectively. It features an intelligent content extraction mechanism that utilizes the Readability algorithm to isolate main content from web pages, removing ads and other non-essential elements. The server supports both HTML and Markdown output formats and enables parallel processing through its fetch_urls tool for concurrent fetching of multiple URLs. Additionally, it optimizes resource usage by automatically blocking unnecessary resources like images and stylesheets, enhancing performance and reducing bandwidth consumption.

DevDocs allows AI assistants to access and process technical documentation, enabling efficient retrieval and understanding of coding resources. It integrates seamlessly with various development tools, enhancing the coding experience by providing quick access to relevant documentation.

Exa MCP Server allows AI assistants to perform web searches using Exa's powerful search API, providing structured results including titles, URLs, and content snippets. It supports real-time web crawling for fresh content and caches recent searches for reference. The server handles rate limiting and error cases gracefully.

Notion MCP Server allows AI assistants to perform various operations within Notion workspaces, including: - Page Operations: Create, read, update, and delete pages. - Database Operations: Create, query, and update databases. - Block Operations: Append, retrieve, update, and delete blocks within pages. - Comment Operations: Add and retrieve comments on pages or blocks. - User Operations: Retrieve information about users within the workspace. This integration enables seamless management and retrieval of content within Notion using AI prompts.

Basic Memory facilitates the creation of a local-first knowledge base by capturing and structuring information from AI assistant interactions. It allows for bidirectional communication between Large Language Models (LLMs) and Markdown files, creating a personal knowledge graph that can be traversed using links between documents. This system supports seamless integration with tools like Obsidian.md, enabling users to visualize and edit their notes effectively.

MCP-Obsidian allows AI assistants to read and search any directory containing Markdown notes, such as an Obsidian vault. It facilitates efficient management and retrieval of notes within Obsidian using AI prompts.

Serena enhances LLMs by providing essential tools for semantic code retrieval and editing. It integrates with existing LLMs, enabling them to perform coding tasks directly within your codebase. Serena supports multiple programming languages through the Language Server Protocol (LSP), including Python, Java, and TypeScript. It can be integrated with LLMs via the Model Context Protocol (MCP) or used with Agno, a model-agnostic agent framework.

MCP-Obsidian enables AI assistants to interact with Obsidian vaults through various tools: - listfilesin_vault: Lists all files and directories in the root directory of your Obsidian vault. - listfilesin_dir: Lists all files and directories in a specific Obsidian directory. - getfilecontents: Returns the content of a single file in your vault. - search: Searches for documents matching a specified text query across all files in the vault. - patch_content: Inserts content into an existing note relative to a heading, block reference, or frontmatter field. - append_content: Appends content to a new or existing file in the vault. - delete_file: Deletes a file or directory from your vault. These tools facilitate efficient management and retrieval of notes within Obsidian using AI prompts.

This package provides both the CLI tooling and the in-Worker logic to connect Claude Desktop (or any MCP Client) to a Cloudflare Worker on your account, so you can customise it to suit your needs. It works via a build step that can translate TypeScript methods of your Worker

GitMCP allows AI assistants to access any GitHub project's documentation seamlessly. By directing the AI to GitMCP, it can retrieve documentation with semantic search capabilities, optimizing token usage. No configurations or modifications are needed—GitMCP works out of the box. It's completely free and private, with no collection of personally identifiable information or queries.

DevDocs enables developers to efficiently crawl, extract, and organize content from technical documentation websites. It streamlines the process of integrating new technologies by providing a centralized, searchable repository of documentation.

Exa MCP Server allows AI assistants to perform web searches using Exa's search API, providing structured results with titles, URLs, and content snippets. It supports real-time web crawling and caches recent searches for reference.

Baidu AI Search MCP Server integrates Baidu's search capabilities with large language models via the Model Context Protocol (MCP), enabling AI assistants to provide intelligent responses with real-time web information.