Mcp RbSAFE
A lightweight Ruby framework for building MCP servers with a Sinatra-like DSL
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A lightweight Ruby framework for implementing MCP (Model Context Protocol) servers with a Sinatra-like DSL.
Installation
Add this line to your application's Gemfile:
gem 'mcp-rb'
Usage
Here's a simple example of how to create an MCP server:
require 'mcp'
name "hello-world"
version "1.0.0"
# Define a resource
resource "hello://world" do
name "Hello World"
description "A simple hello world message"
call { "Hello, World!" }
end
# Define a resource template
resource_template "hello://{user_name}" do
name "Hello User"
description "A simple hello user message"
call { |args| "Hello, #{args[:user_name]}!" }
end
# Define a tool
tool "greet" do
description "Greet someone by name"
argument :name, String, required: true, description: "Name to greet"
call do |args|
"Hello, #{args[:name]}!"
end
end
# Define a tool with nested arguments
tool "greet_full_name" do
description "Greet someone by their full name"
argument :person, required: true, description: "Person to greet" do
argument :first_name, String, required: false, description: "First name"
argument :last_name, String, required: false, description: "Last name"
end
call do |args|
"Hello, First: #{args[:person][:first_name]} Last: #{args[:person][:last_name]}!"
end
end
# Define a tool with an Array argument
tool "group_greeting" do
description "Greet multiple people at once"
argument :people, Array, required: true, items: String, description: "People to greet"
call do |args|
args[:people].map { |person| "Hello, #{person}!" }.join(", ")
end
endSupported specifications
Reference: MCP 2024-11-05
- Base Protocol
- ping
- stdio transport
- Server features
- Resources
- resources/read
- resources
bd9be72afbbeOBSERVED · 2026-10-06Exposed tools (3)
3 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
list_users | read | List users with their details |
sum_numbers | read | Sum an array of numbers |
test_tool | read | Test tool |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (3)
require_relative "../../test_helper"
require_relative "../../test_helper"
require_relative "../../test_helper"
Gates applied: no_behavioural_pass.
bd9be72afbbefull audit observations/trust-audit/mcp-server/funwarioisii__mcp-rb.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-06 | bd9be72afbbe | SAFE | B | 89 | first audit |
Questions
What is the Mcp Rb MCP server?
A lightweight Ruby framework for building MCP servers with a Sinatra-like DSL
What tools does Mcp Rb expose?
3 in total: 3 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Mcp Rb safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Mcp Rb need?
No credential environment variables were found in its source, so it appears to need none.
How current is this page?
The grade is for one exact copy of the source (bd9be72afbbe), read on 2026-10-06. The repository is watched and re-audited when it changes.