
Wraps the Chess.com public API so you can pull player profiles, game history, ratings, and tournament data directly into Claude. No authentication needed since it uses Chess.com's free public endpoints. Hosted through Pipeworx's gateway infrastructure, which means you can either connect to this specific chess feed or tap into their full 673+ source catalog through a single MCP endpoint. The ask_pipeworx tool lets you query in natural language instead of calling specific functions. Reach for this when you're building chess analytics, player comparisons, or any workflow that needs live data from Chess.com without managing API keys or rate limits yourself.
Chess.com MCP — wraps the Chess.com public API (free, no auth)
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
| Tool | Description |
|---|---|
get_player | Get a Chess.com player's profile by username (e.g., 'hikaru'). Returns title, country, followers, join date, and last online time. |
get_stats | Get a CHESS.COM player's ratings and game records across daily, rapid, blitz, and bullet formats. PREFER for "'s blitz/bullet/rapid rating on Chess.com", "what is rated on Chess.com". Returns current/best ratings and win/loss/draw counts. |
get_games | Retrieve a player's completed games for a specific month (format: YYYY/MM, e.g., '2024/01'). Returns game URLs, time controls, results, and ratings. |
get_leaderboards | Check top-ranked Chess.com players by format (daily, rapid, blitz, bullet). Returns rankings with ratings and win percentages. |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"chess": {
"url": "https://gateway.pipeworx.io/chess/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/chess/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, 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 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Chess data" })
The gateway picks the right tool and fills the arguments automatically.
MIT