What transport does VectorMCP use?
VectorMCP ships with streamable HTTP as its built‑in transport, supporting `POST /mcp` for JSON‑RPC messages, `GET /mcp` for SSE streams, and `DELETE /mcp` for session termination.
@sergiobayona
Basic information
A server implementation for the Model Context Protocol (MCP) in Ruby.
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
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. It is designed for Ruby developers building MCP‑compliant servers, especially those using Rack or Rails.
Install the gem (gem install vector_mcp), require it in Ruby, then create a VectorMCP::Server instance, register tools (either class‑based via VectorMCP::Tool or block‑based via register_tool), and call server.run(port: 8080). The server can also be mounted inside a Rack app or Rails routes using server.rack_app.
rack_appVectorMCP ships with streamable HTTP as its built‑in transport, supporting `POST /mcp` for JSON‑RPC messages, `GET /mcp` for SSE streams, and `DELETE /mcp` for session termination.
Yes. Pass a `resource_metadata_url:` to `enable_authentication!` to enable RFC 9728 discovery. Unauthenticated requests return a `401` with a `WWW‑Authenticate` header pointing to the metadata document.
Ruby 3.2 or higher.
Yes. VectorMCP can be mounted in Rails routes via `mount MCP_APP => "/mcp"`. It also includes `VectorMCP::Rails::Tool` for ActiveRecord‑backed tools.
The `VectorMCP::Middleware::Anonymizer` replaces sensitive string values with stable opaque tokens on outbound tool results and restores them on inbound tool arguments, keeping the original data hidden from the LLM.

Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3
A curated list of references for MLOps
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct
Hindsight: Agent Memory That Learns

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.
Comments