speedrun.com MCP server for AI agents
Let Claude, ChatGPT or your own agent read speedrun.com: 3 typed functions through one MCP server. No speedrun.com API key needed.
- Site
- speedrun.com
- Functions
- 3
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just speedrun.com
An MCP server for speedrun.com alone, with one tool per function. Paste it into Claude, ChatGPT, Cursor or any MCP client as a remote server.
https://api.bowmark.ai/mcp/site/speedrunEvery site
One MCP server for speedrun.com and every other site Bowmark covers. Your agent looks up what it needs and calls it.
https://api.bowmark.ai/mcpSet it up in your clientBoth need a Bowmark API key. The quickstart gets you one and a first result in a few minutes.
Functions
Open a function to see its arguments, what it returns and how to call it.
Read 3
categoriesList all categories for a game, including variables and values.Arguments
Name Type Required gameIdstringYes Returns
Category[]interface Category { id: string; name: string; weblink: string; type: string; // "per-game" | "per-level" rules?: string; players?: { type: string; value?: number } miscellaneous?: boolean; // hidden from the default leaderboard view variables?: { data: CategoryVariable[] } } interface CategoryVariable { id: string; name: string; mandatory: boolean; "user-defined": boolean; // submitRun takes the KEY of a choice, never its label values?: { choices?: Record<string, { label: string }>; default?: string } }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/speedrun/categoriesCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.speedrun.categories({ gameId: "76rxvqq6" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.speedrun.categories({"gameId": "76rxvqq6"}))curl -X POST https://api.bowmark.ai/v1/sites/speedrun/categories \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"gameId":"76rxvqq6"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.speedrun.categories({ gameId: "76rxvqq6" });findGameSearch for a game by name, returning metadata including ID, platforms, and rules.Arguments
Name Type Required namestringYes Returns
Game[]interface Game { id: string; names: { international: string; japanese?: string }; abbreviation: string; weblink: string; released: number; "release-date": string; platforms?: string[]; ruleset?: { "require-video": boolean; "require-verification": boolean; "show-milliseconds": boolean }; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/speedrun/findGameCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.speedrun.findGame({ name: "Wetrix" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.speedrun.findGame({"name": "Wetrix"}))curl -X POST https://api.bowmark.ai/v1/sites/speedrun/findGame \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"name":"Wetrix"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.speedrun.findGame({ name: "Wetrix" });platformsList all platforms, optionally filtered to a specific game.Arguments
Name Type Required gameIdstringNo Returns
Platform[]interface Platform { id: string; name: string; released?: number; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/speedrun/platformsCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.speedrun.platforms();import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.speedrun.platforms())curl -X POST https://api.bowmark.ai/v1/sites/speedrun/platforms \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.speedrun.platforms();
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/speedrun/<function> - OpenAPI
/v1/sites/speedrun/openapi.json