VectorMCP
A Ruby gem for building Model Context Protocol (MCP) servers to expose tools, resources, and prompts to LLM clients.
VectorMCP
VectorMCP is a Ruby implementation of the Model Context Protocol (MCP) server-side specification. It gives you a framework for exposing tools, resources, prompts, roots, sampling, middleware, and security over the MCP streamable HTTP transport.
Highlights
- Streamable HTTP is the built-in transport, with session management, resumability, and MCP 2025-11-25 compliance
- Class-based tools via
VectorMCP::Tool, plus the original block-basedregister_toolAPI - Rack and Rails mounting through
server.rack_app - Opt-in authentication and authorization, structured logging, and middleware hooks
- Image-aware tools/resources/prompts, roots, and server-initiated sampling
- Token-based field anonymization middleware to keep sensitive values out of LLM context
Requirements
- Ruby 3.2+
Installation
gem install vector_mcp
gem "vector_mcp"
Quick Start
require "vector_mcp"
class Greet < VectorMCP::Tool
description "Say hello to someone"
param :name, type: :string, desc: "Name to greet", required: true
def call(args, _session)
"Hello, #{args["name"]}!"
end
end
server = VectorMCP::Server.new(name: "MyApp", version: "1.0.0")
server.register(Greet)
server.run(port: 8080)
The class-based DSL is optional. The existing block-based API still works:
server.register_tool(
name: "echo",
description: "Echo back the supplied text",
input_schema: {
type: "object",
properties: { text: { type: "string" } },
required: ["text"]
}
) { |args| args["text"] }
Rack and Rails
VectorMCP can run as a standalone HTTP server or be mounted inside an existing Rack app:
require "vector_mcp"
server = VectorMCP::Server.new(name: "MyApp", version: "1.0.0")
server.register(Greet)
MCP_APP = server.rack_app
In Rails, mount it in config/routes.rb:
mount MCP_APP => "/mcp"
For ActiveRecord-backed tools, opt into VectorMCP::Rails::Tool:
require "vector_mcp/rails/tool"
class FindUser < VectorMCP::Rails::Tool
description "Find a user by id"
param :id, type: :integer, required: true
def call(args, _session)
user = find!(User, args[:id])
{ id: user.id, email: user.email }
end
end
See docs/rails-setup-guide.md for a full setup guide.
Tools, Resources, and Prompts
Expose callable tools:
server.register_tool(
name: "calculate",
description: "Performs basic math",
input_schema: {
type: "object",
properties: {
operation: { type: "string", enum: ["add", "subtract", "multiply"] },
a: { type: "number" },
b: { type: "number" }
},
required: ["operation", "a", "b"]
}
) do |args|
case args["operation"]
when "add" then args["a"] + args["b"]
when "subtract" then args["a"] - args["b"]
when "multiply" then args["a"] * args["b"]
end
end
Expose readable resources:
server.register_resource(
uri: "file://config.json",
name: "App Configuration",
description: "Current application settings"
) { File.read("config.json") }
Define prompt templates:
server.register_prompt(
name: "code_review",
description: "Reviews code for best practices",
arguments: [
{ name: "language", description: "Programming language", required: true },
{ name: "code", description: "Code to review", required: true }
]
) do |args|
{
messages: [{
role: "user",
content: {
type: "text",
text: "Review this #{args["language"]} code:\n\n#{args["code"]}"
}
}]
}
end
VectorMCP::Tool also supports type: :date and type: :datetime, which are validated as strings in JSON Schema and coerced to Date and Time before #call runs.
Security and Middleware
VectorMCP keeps security opt-in, but the primitives are built in:
server.enable_authentication!(
strategy: :api_key,
keys: ["your-secret-key"]
)
server.enable_authorization! do
authorize_tools do |user, _action, tool|
user[:role] == "admin" || !tool.name.start_with?("admin_")
end
end
Custom authentication works too:
server.enable_authentication!(strategy: :custom) do |request|
api_key = request[:headers]["X-API-Key"]
user = User.find_by(api_key: api_key)
user ? { user_id: user.id, role: user.role } : false
end
For MCP clients that speak OAuth 2.1 (e.g. Claude Desktop), pass a resource_metadata_url: to turn on RFC 9728 discovery. Unauthenticated requests to /mcp return 401 with a WWW-Authenticate header pointing at the configured metadata document, and the client drives the rest of the OAuth dance automatically. See docs/oauth_resource_server.md for the feature reference and docs/rails_oauth_integration.md for a full Rails + Doorkeeper recipe.
Middleware can hook into tool, resource, prompt, sampling, auth, and transport events, including before_auth, after_auth, on_auth_error, before_request, after_response, and on_transport_error.
See security/README.md for the full security guide.
Field Anonymization
Keep sensitive string values out of the LLM context by substituting them with stable opaque tokens. Values are tokenized on outbound tool results and restored on inbound tool arguments, so the LLM sees only tokens while your handlers receive the original data.
anonymizer = VectorMCP::Middleware::Anonymizer.new(
store: VectorMCP::TokenStore.new,
field_rules: [
{ pattern: /email/i, prefix: "EMAIL" },
{ pattern: /\bssn\b/i, prefix: "SSN" }
]
)
anonymizer.install_on(server)
Transport Notes
- VectorMCP ships with streamable HTTP as its built-in transport
POST /mcpaccepts a single JSON-RPC request, notification, or response; batch arrays are rejectedGET /mcpopens an SSE stream for server-initiated messagesDELETE /mcpterminates the session- The server advertises MCP protocol
2025-11-25and accepts2025-03-26and2024-11-05headers for compatibility - Default allowed origins are restricted to localhost and loopback addresses
Initialize a session with curl:
curl -X POST http://localhost:8080/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-11-25","capabilities":{},"clientInfo":{"name":"curl","version":"1.0"}}}'
More Features
- Roots via
register_rootandregister_root_from_path - Image resources and image-aware tools/prompts
- Structured logging with component loggers
- Server-initiated sampling with streaming/tool-call support
- Middleware-driven request shaping and observability
Documentation
- CHANGELOG.md
- examples/
- docs/rails-setup-guide.md
- docs/rails_oauth_integration.md
- docs/oauth_resource_server.md
- docs/streamable-http-spec-compliance.md
- security/README.md
- MCP Specification
Contributing
Bug reports and pull requests are welcome on GitHub.
License
Available as open source under the MIT License.
関連サーバー
Alpha Vantage MCP Server
スポンサーAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
Oso Cloud MCP Server
Understand, develop, and debug authorization policies in Oso Cloud.
Grovs
MCP server for managing deep links, analytics, and app configuration on Grovs.io. Works with Claude Code, Cursor, Windsurf, and any MCP-compatible client.
HandMirrorMcp
A Model Context Protocol (MCP) server for .NET assembly and NuGet package inspection
SpecBridge
Automatically generates MCP tools from OpenAPI specifications by scanning a folder for spec files. No configuration is needed and it supports authentication via environment variables.
LetzAI
An MCP server for image generation using the LetzAI API.
jpx
JMESPath query tool with 320+ extended functions for JSON transformation and analysis
Agentic Control Framework (ACF)
A toolkit for autonomous agent development with tools for task management, filesystem operations, browser automation, and terminal control.
Gitlab MCP Server
Model Context Protocol (MCP) server for GitLab — exposes 1006 GitLab REST & GraphQL API operations as MCP tools (28 meta-tools / 43 enterprise), 24 resources, 38 prompts, and 17 completion types for AI assistants. Written in Go, single static binary, stdio and HTTP transport.
Remote MCP Server (Authless)
An example of a remote MCP server deployable on Cloudflare Workers, without authentication.
MCPJungle
A self-hosted MCP Server registry for private AI agents, supporting both PostgreSQL and SQLite databases.