{
  "markdown": "# mcp-speedrun\n\nSpeedrun.com MCP — wraps the Speedrun.com API v1 (speedrun.com/api/v1)\n\nPart of [Pipeworx](https://pipeworx.io) — an MCP gateway connecting AI agents to 1476+ live data sources.\n\n## Tools\n\n| Tool | Description |\n|------|-------------|\n| `search_games` | Search the Speedrun.com database for games by name. Returns matching games with their ID (needed for get_categories and get_leaderboard), abbreviation, release year, and weblink. Example: search_games({ query: \"super mario 64\", max: 5 }) |\n| `get_categories` | List the run categories for a game (e.g. \"Any%\", \"100%\", \"Glitchless\"). Use the game ID from search_games. Each category has an ID needed to fetch a leaderboard via get_leaderboard. Example: get_categories({ game_id: \"o1y9wo6q\" }) |\n| `get_leaderboard` | Fetch the world-record / top-N leaderboard for a specific game category. Returns ranked runs with finish times (ISO-8601 duration plus seconds), run date, players, and weblink. Get game_id from search_games and category_id from get_categories. Example: get_leaderboard({ game_id: \"o1y9wo6q\", category_id: \"7kjpp4k3\", top: 10 }) |\n| `find_user` | Look up a speedrunner by username. Returns matching users with their ID, display name, and profile weblink. Example: find_user({ name: \"cheese05\" }) |\n\n## Quick Start\n\nAdd to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):\n\n```json\n{\n  \"mcpServers\": {\n    \"speedrun\": {\n      \"url\": \"https://gateway.pipeworx.io/speedrun/mcp\"\n    }\n  }\n}\n```\n\n### What this endpoint actually serves\n\n`tools/list` at `https://gateway.pipeworx.io/speedrun/mcp` returns the tools in the table\nabove **plus the shared Pipeworx meta-tools** — `ask_pipeworx`,\n`discover_tools`, `search_within`, `remember`/`recall` and the rest of the\ngateway-wide set. So the tool count you see is larger than this table: a\nsingle-pack endpoint currently lists roughly 30 shared tools alongside the\npack's own. The connection's `initialize` response states its exact scope, and\nis the authoritative answer for a given day.\n\nThis is deliberate, not multiplexing by accident. The meta-tools are what let a\nscoped connection answer a question this pack does not cover — via\n`ask_pipeworx`, which routes across the whole catalog — without you adding a\nsecond MCP server. There is currently no way to mount a pack endpoint without\nthem; if the extra schemas cost you more context than the routing is worth,\nconnect to the full gateway once rather than to several pack endpoints.\n\nOr connect to the full Pipeworx gateway to get every pack's tools listed\ndirectly, instead of just this one's:\n\n```json\n{\n  \"mcpServers\": {\n    \"pipeworx\": {\n      \"url\": \"https://gateway.pipeworx.io/mcp\"\n    }\n  }\n}\n```\n\nBoth URLs reach the same gateway and the same 1476+ data sources. The\nonly difference is which pack's tools are listed **directly**; `ask_pipeworx`\nreaches all of them from either one.\n\n## Using with ask_pipeworx\n\nInstead of calling tools directly, you can ask questions in plain English —\nthis works on the pack endpoint above as well as on the full gateway:\n\n```\nask_pipeworx({ question: \"your question about Speedrun data\" })\n```\n\nThe gateway picks the right tool and fills the arguments automatically.\n\n## More\n\n- [Docs and guides](https://pipeworx.io/docs)\n- [pipeworx.io](https://pipeworx.io)\n\n## License\n\nMIT\n",
  "bytes": 3316,
  "sha": "f3784ad5d9d09071a0b9762a85ceabee7da94c7939cfef450a835e3cf679bd74",
  "repo_slug": "pipeworx-io/mcp-speedrun",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_pipeworx_io_speedrun_7c66fa32/readme"
}