MCP server and API for Steam game recommendations from imho.run: games like any
MCP server and API for Steam game recommendations from imho.run: games like any game, game facts, find a game from a description. Docs, configs and a Python client.
active Production-safe Score 94/100 http no auth
At a glance
| Endpoint | https://imho.run/mcp |
|---|---|
| Source | https://github.com/0x216/imho-mcp |
| Transport | http |
| Tools | 8 |
| Auth | none |
| First seen | 2026-10-06 01:29:45 |
| Last checked | 2026-11-17 21:53:20 |
Observed reliability
| 7-day uptime | 100% |
|---|---|
| 24-hour uptime | 100% |
| Handshake success | 100% |
| Latency p50 / p95 | 390 / 603 ms |
| Last successful check | 2026-11-17 21:53:20 |
Measured by Arclan's validator via repeated live MCP handshakes. How this is computed →
Tools (8)
games_like— Steam games similar to ONE game, ranked by imho.run's recommender (the list on that game's imho.run page), each with a one-line reason, pricrecommend— Steam games for someone who likes 1-3 given games, ranked by imho.run's recommender: the list imho.run's own tool shows for those games andlibrary_recs— Steam games for a player, ranked against their own public Steam library (what they play most), the way imho.run's library mode does it; ownegame_facts— Public facts about one Steam game: year, developers, genres, top tags, price, Steam Deck status, review numbers, a review-mined summary andfind_game_by_description— Identify a game from a description of what the user remembers (plot, look, platform, era). Returns ranked candidates with a reason each, a `trending— Steam games trending right now (imho.run/trending): `rising` = established games gaining reviews and players against their own recent baselinew_releases— Games released on Steam in the last 30 days that players rate well (70%+ positive, 50+ positive reviews), or with `upcoming` the upcoming gasearch_games— Find Steam games by title (typos, partial names, Russian names and acronyms are fine): appid, year, imho.run page and Steam link for each ma
Validation history
| Checked | Reachable | Handshake | Latency | Score | State |
|---|---|---|---|---|---|
| 2026-11-17 21:53:20 | ✓ | ✓ | 194 ms | 94 | active |
| 2026-11-17 21:38:15 | ✓ | ✓ | 250 ms | 94 | active |
| 2026-11-17 21:22:56 | ✓ | ✓ | 247 ms | 94 | active |
| 2026-11-17 21:07:37 | ✓ | ✓ | 350 ms | 91 | active |
| 2026-11-17 20:52:36 | ✓ | ✓ | 224 ms | 94 | active |
| 2026-11-17 20:37:35 | ✓ | ✓ | 469 ms | 91 | active |
| 2026-11-17 20:22:28 | ✓ | ✓ | 395 ms | 91 | active |
| 2026-11-17 20:07:24 | ✓ | ✓ | 586 ms | 91 | active |
| 2026-11-17 19:51:38 | ✓ | ✓ | 483 ms | 91 | active |
| 2026-11-17 19:36:31 | ✓ | ✓ | 255 ms | 94 | active |
| 2026-11-17 19:21:19 | ✓ | ✓ | 257 ms | 94 | active |
| 2026-11-17 19:06:05 | ✓ | ✓ | 223 ms | 94 | active |
| 2026-11-17 18:50:53 | ✓ | ✓ | 273 ms | 94 | active |
| 2026-11-17 18:35:44 | ✓ | ✓ | 408 ms | 91 | active |
| 2026-11-17 18:20:43 | ✓ | ✓ | 279 ms | 94 | active |
Query this programmatically
Agents can pull this record live over the MCP protocol or REST:
get_server("https://imho.run/mcp") # via the Arclan MCP endpoint https://arclan.ai/mcp
GET https://arclan.ai/api/registry/imho-run-mcp # JSON