Igdb MCP server

@pipeworx/igdb

IGDB (Internet Game Database, Twitch/Amazon) — the reference catalogue for ~300,000 video games: release dates per platform, genres, ratings, developers, publishers, franchises and cover art.

Part of Pipeworx — an MCP gateway connecting AI agents to 1679+ live data sources.

Tools

• igdbsearchgames(query) — search games by title, optionally scoped to a platform or a release window.
• igdb_game(id | slug) — one game in full, with per-platform release dates, DLC, expansions and similar titles.
• igdb_companies(query) — developers and publishers, with what they shipped.
• igdb_platforms(query) — the ~200 platforms, whose ids scope a game search.

Auth

Platform key (PLATFORMTWITCHKEY) with BYO override via _apiKey.

The credential is the same Twitch app the twitch pack uses — IGDB is gated by Twitch OAuth, so apiKey is "CLIENTID:CLIENTSECRET" and the pack exchanges it for an app access token per call. No new gateway binding was added for this pack; it declares the existing PLATFORMTWITCH_KEY.

Callers who want their own rate budget get credentials free at .

Data sources

• — client-credentials grant.
• , /companies, /platforms — POST, Apicalypse body.

Notes the next person would otherwise rediscover:

search "zelda"; limit 10; — every clause ends in a semicolon.

• The API is POST-only and the body is a DSL, not JSON. fields name,summary;

That is the silent-zero trap here; this pack always sends an explicit list.

• fields is mandatory and omitting it returns empty objects, not an error.

relevance-ranked; where name ~ "x" is a sortable substring filter. The game and company tools use the first, igdb_platforms the second.

• search and sort cannot appear in the same query. search "x" is

date is also returned as an ISO day.

• firstreleasedate and startdate are unix seconds**, not strings. Every

https://images.igdb.com/igdb/image/upload//.jpg.

• Cover/logo image_id values become URLs as

this pack pair with twitch.

• IGDB game ids and Twitch game ids are the same id space, which is what makes

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "igdb": {
      "url": "https://gateway.pipeworx.io/igdb/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/igdb/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — askpipeworx, discovertools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1679+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

Shortened. The full README is on GitHub.