ada-diamonds-mcp

ada-diamonds-mcp is a skill for Claude Code, Codex from adadiamonds/agent-tools. It costs 98 tokens per session (2,035 once invoked), scanned A, original, MIT.

A connection guide for Ada Diamonds' MCP servers, which provide access to a diamond and jewelry catalogue plus read-only documentation. MCP is a standard way for AI tools to use external services.

In plain words
What is it for?
Use it when configuring Claude Code, Claude Desktop, Cursor, ChatGPT, or another Streamable HTTP MCP client to browse Ada Diamonds products, guides, company information, and developer docs.
Why use it?
It explains how to connect supported coding and AI clients to the catalogue and its documentation.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument; mentions Claude Code.

Good fit Use it when configuring Claude Code, Claude Desktop, Cursor, ChatGPT, or another Streamable HTTP MCP client to browse Ada Diamonds products, guides, company information, and developer docs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/adadiamonds/agent-tools/ada-diamonds-mcp
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add adadiamonds/agent-tools --skill ada-diamonds-mcp
Clone the repo
git clone --depth 1 https://github.com/adadiamonds/agent-tools

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ada-diamonds-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/adadiamonds/agent-tools/ada-diamonds-mcp/github.svg)](https://agentmods.dev/skills/adadiamonds/agent-tools/ada-diamonds-mcp)
Your own site
<a href="https://agentmods.dev/skills/adadiamonds/agent-tools/ada-diamonds-mcp"><img src="https://agentmods.dev/badge/skills/adadiamonds/agent-tools/ada-diamonds-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ada-diamonds-mcp

Your own site · 80×15
<a href="https://agentmods.dev/skills/adadiamonds/agent-tools/ada-diamonds-mcp"><img src="https://agentmods.dev/badge/skills/adadiamonds/agent-tools/ada-diamonds-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,035 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00098 $0.02035
Opus 5 $0.00049 $0.01018
Sonnet 5 $0.00020 $0.00407
Haiku 4.5 $0.00010 $0.00203

Measured 10d ago against content hash a2ac93a95f50, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ada-diamonds-mcp scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X POST https://www.adadiamonds.com/mcp \
skills/ada-diamonds-mcp/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ada Diamonds MCP servers

Two Streamable HTTP servers, both anonymous for catalog and content. No OAuth handshake before tools/list.

Server URL Purpose
ada-diamonds https://www.adadiamonds.com/mcp Live catalog: diamonds, settings, jewelry, guides, company info, consultations
ada-diamonds-docs https://www.adadiamonds.com/mcp/docs Read-only: the developer documentation itself (search_docs, read_doc, list_docs)

Registry name: com.adadiamonds/ada-diamonds. Server cards: https://www.adadiamonds.com/.well-known/mcp/server-card.json (also /mcp/server-card) and https://www.adadiamonds.com/.well-known/mcp/docs-server-card.json (also /mcp/docs/server-card). Registry manifest: https://www.adadiamonds.com/server.json. A plain GET on either server URL describes it.

This repository ships both in mcp.json (Agent Plugins format), so a client that installs the plugin gets them without further configuration.

Connect

Claude Code

claude mcp add --transport http ada-diamonds https://www.adadiamonds.com/mcp
claude mcp add --transport http ada-diamonds-docs https://www.adadiamonds.com/mcp/docs

Or in .mcp.json at the project root:

{
  "mcpServers": {
    "ada-diamonds": { "type": "http", "url": "https://www.adadiamonds.com/mcp" },
    "ada-diamonds-docs": { "type": "http", "url": "https://www.adadiamonds.com/mcp/docs" }
  }
}

Claude Desktop and claude.ai

Either add it as a connector (Settings, Connectors, "Add custom connector", URL https://www.adadiamonds.com/mcp), or put it in claude_desktop_config.json (Settings, Developer, Edit Config) and restart:

{
  "mcpServers": {
    "ada-diamonds": { "type": "http", "url": "https://www.adadiamonds.com/mcp" }
  }
}

No OAuth prompt appears for the public tools; request_consultation asks for consent when first used.

Cursor

.cursor/mcp.json (project) or ~/.cursor/mcp.json (global):

{
  "mcpServers": {
    "ada-diamonds": { "url": "https://www.adadiamonds.com/mcp" },
    "ada-diamonds-docs": { "url": "https://www.adadiamonds.com/mcp/docs" }
  }
}

Read the full file on GitHub · 143 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 143 lines · 98 tokens per session scan A a2ac93a95f50

Subscribe to this mod's changes

ada-diamonds-mcp is a skill published in the GitHub repository adadiamonds/agent-tools (2 stars, last pushed 13d ago), licensed MIT. It adds 98 tokens to every session and 2,035 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories