About NDEX Pricing
NDEX Pricing is a read-only MCP server for looking up Swiss market prices for video games and consoles. It separates observed Swiss prices from external PAL references and includes sample size, freshness, and confidence details.
Key features
- 01Search the NDEX game and console catalog
- 02Retrieve Swiss observed price estimates
- 03View external PAL references separately
- 04Check sample size, freshness, and confidence
Use cases
- 01Check Swiss market prices for a game
- 02Compare observed prices with PAL references
- 03Assess how current and well-supported an estimate is
MCP support
The remote MCP server exposes catalog search and price estimate tools to clients. It uses OAuth 2.1 authorization and performs read-only access.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://www.nd-x.app/api/mcpclaude mcp add --transport http app-nd-x-ndex-pricing https://www.nd-x.app/api/mcp{"mcpServers":{"app-nd-x-ndex-pricing":{"type":"http","url":"https://www.nd-x.app/api/mcp"}}}Open in Cursor{"servers":{"app-nd-x-ndex-pricing":{"type":"http","url":"https://www.nd-x.app/api/mcp"}}}Open in VS Code{"mcpServers":{"app-nd-x-ndex-pricing":{"type":"http","url":"https://www.nd-x.app/api/mcp"}}}{"mcpServers":{"app-nd-x-ndex-pricing":{"serverUrl":"https://www.nd-x.app/api/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMENDEX Pricing — MCP connector
Swiss market prices for video games and consoles, with provenance, served to any MCP client from
https://www.nd-x.app/api/mcp. Read-only: two tools, one scope, no writes.
| Tool | What it does |
|---|---|
search_ndex_catalog | Find a game or console in the NDEX catalog (platform disambiguates homonyms). |
get_ndex_estimate | Swiss observed prices and external PAL references, kept separate, with sample size, freshness and confidence. |
The skill in skills/ndex-pricing/ teaches the model how to use them: identify first, never average
sources of different provenance, say when the price is unknown.
Connect
ChatGPT, claude.ai, Claude Desktop — add https://www.nd-x.app/api/mcp as a connector. The server
is its own OAuth 2.1 authorization server (PKCE S256, Client ID Metadata Documents, dynamic registration
as fallback). You sign in with your NDEX account and consent once.
In ChatGPT, a remote server is registered through developer mode (Plugins → new connection with the
URL above); ChatGPT assigns it an id starting with plugin_asdk_app_. A ChatGPT / Codex plugin then
references that registration through an .app.json file named by the apps field of
.codex-plugin/plugin.json. This repository ships the manifest and the skill; the .app.json is
produced at registration time, so it is not committed here.
Claude Code — install this plugin, or add the server directly:
claude mcp add --transport http ndex-pricing https://www.nd-x.app/api/mcp
Claude Code identifies itself with its Client ID Metadata Document and completes the OAuth flow in your browser. No token to paste.
Codex, Cursor, VS Code, Gemini CLI, Windsurf, Zed, Warp — point the client at the same URL. Clients that only support a static header can use a beta bearer token, handed out on request at nd-x.app/mcp.
Layout
.claude-plugin/plugin.json— Claude Code / Cowork plugin manifest (skill + remote MCP server in.mcp.json)..codex-plugin/plugin.json— ChatGPT / Codex plugin manifest (skill; the remote server is attached throughapps→.app.jsononce registered in ChatGPT, see above).server.json— entry for the official MCP registry, published asapp.nd-x/ndex-pricing.skills/ndex-pricing/SKILL.md— the skill, in French (the model follows it in any language).
Privacy and terms
nd-x.app/privacy. The connector reads catalog and price data only; it never touches your collection, your account, or the conversation.
Support: [email protected]
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.