What runtime dependencies does VectorMCP require?
Ruby 3.2 or later is required. The gem has no other mandatory runtime dependencies beyond the Ruby standard library.
@sergiobayona
基本信息
A server implementation for the Model Context Protocol (MCP) in Ruby.
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
VectorMCP is a Ruby implementation of the Model Context Protocol (MCP) server-side specification. It provides a framework for exposing tools, resources, prompts, roots, sampling, middleware, and security over the MCP streamable HTTP transport.
Install the gem (gem install vector_mcp), create a VectorMCP::Server, register tools (using either the class-based VectorMCP::Tool DSL or the block-based register_tool API), and call server.run(port: 8080). Optionally mount the server in a Rack or Rails app via server.rack_app.
VectorMCP::Tool and block-based register_tool APIserver.rack_appRuby 3.2 or later is required. The gem has no other mandatory runtime dependencies beyond the Ruby standard library.
VectorMCP ships with streamable HTTP as its built-in transport. It supports `POST /mcp` for JSON-RPC, `GET /mcp` for SSE streams, and `DELETE /mcp` for session termination.
Authentication is opt-in. You can enable API key authentication or a custom strategy. For OAuth 2.1 (RFC 9728) support, provide a `resource_metadata_url:` to enable automatic discovery and the OAuth dance.
Yes. VectorMCP provides a `VectorMCP::Rails::Tool` base class for ActiveRecord-backed tools and a full guide for mounting the server in `config/routes.rb`.
Yes. The server advertises MCP protocol version `2025-11-25` and accepts `2025-03-26` and `2024-11-05` headers for compatibility.
Memlord is a remote MCP server available at https://app.memlord.com.

The official Semantic-UI-React integration

Islamic source data for assistants: Quran, hadith, tafsir, duas, prayer times and qibla. Answers come from real sources with citations instead of recalled text, so verses and hadith are not hallucinated. 36,000+ hadiths

Shared memory for AI coding agents. Claude Code, Cursor and Codex read your project's decisions, lessons and tasks before they act.

One permissioned folder your team and your AI agents both log into.
评论