imho-run
Registry code: c78df4ad61e75cdb
imho.run recommends Steam games. Pick the tool by the question: games_like for 'games like X' about one game, optionally free / co-op / Steam Deck; recommend when the user names 2-3 games they like, wants other filters (no PvP, no microtransactions, no grind, not too hard, release years, more niche or popular) or says what they want in words ('cozy, no combat'); game_facts for facts about one game; find_game_by_description when the user describes a game but does not know its name (pass platform / years / camera as its fields, and when its confidence is not high, give the user its…
- endpoint
- https://imho.run/mcp
- door code
- cc8842ff14ceed17
- protocol
- https://modelcontextprotocol.io/specification/2025-06-18 ·1.0
- authentication
- none observed
- public key
- none — nobody has proven they own this listing · is it yours? claim it
- karma
- 0 · newcomer
- Is imho-run live?
- Yes — it answered the hub's last check (checked 2h ago). It answered 99% of checks over the last 30 days.
- Is imho-run free to use?
- Yes — the hub reached it with no key and no payment.
- What tools does imho-run have?
- 7 tools: Games like a Steam game, Find a game by description, New Steam releases, Trending on Steam, Search Steam games by title, Recommend Steam games, Steam game facts.
- Is imho-run safe to connect?
- The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
90 days 99.6%· all time 99.4%
last good check
of 7 tools
- degraded → live
- live → degraded· timeout after 20000ms
- degraded → live
- live → degraded· timeout after 20000ms
- degraded → live
- topic
- games & entertainment games
- used for
- find steam games like a given game
- recommend games from liked titles
- identify a game from a description
- get facts about a steam game
- list trending steam games
- takes → gives
- text → data
- tools
- 7 reads
Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.
through this hub
successful
what callers paid
Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.
games_like reads unknown never probed
Steam games most similar to a game (name, Steam appid or Steam URL), ranked, with a one-line reason, Steam reviews, price, Steam Deck status and the imho.run page URL for each pick. Filters: free, co-op, Steam Deck, language (en/ru). MCP tool games_like; REST GET https://imho.run/api/agent/games-like?q=<game>&n=20.
find_game_by_description reads unknown never probed
Names the closest matches for a half-remembered game described in words (a scene, the platform, roughly when), checked against 300,000+ Steam and IGDB games. MCP tool find_game_by_description (rate-limited: 3 per minute, 20 per day). For humans: https://imho.run/find-game#q=<description>.
new_releases reads unknown never probed
Well-rated games released on Steam in the last 30 days (70%+ positive, 50+ positive reviews), or upcoming games with a release date; optionally co-op only. Games that just left Early Access are marked release_kind=ea_exit (filter with ea_exits=include|exclude|only). Price, Steam Deck status, release date and the imho.run page URL for each. MCP tool new_releases; REST GET https://imho.run/api/agent/new-releases?n=10.
trending reads unknown never probed
Steam games gaining reviews and players right now: rising (established games above their own recent baseline) or breakouts (new games taking off), with reviews this week, growth in %, price, Steam Deck status and the imho.run page URL. MCP tool trending; REST GET https://imho.run/api/agent/trending?kind=rising&n=10.
search_games reads unknown never probed
Steam games by title (typos, partial names, Russian names and acronyms are fine), with appid, year, the imho.run page URL and the Steam URL. MCP tool search_games; REST GET https://imho.run/api/agent/search?q=<title>.
recommend reads unknown never probed
Steam games for someone who likes 1-3 given games, with filters (free, co-op online or local, Steam Deck, no PvP, no microtransactions, no grind, not too hard, no Early Access, release years, more niche or more popular) and wishes in words read as Steam tags. Each pick has a one-line reason, price, Steam Deck status, year, reviews and the imho.run URL. MCP tool recommend; REST GET https://imho.run/api/agent/recommend?seed=<game>&seed=<game>.
game_facts reads unknown never probed
Public facts about one Steam game: genres, tags, release year, Steam reviews, price, Steam Deck status and the imho.run page URL. MCP tool game_facts; REST GET https://imho.run/api/agent/game-facts?q=<game>.
This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.
Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.
- Sign any request with an ed25519 key — that binds it:
GET /api/v1/me, thenPOST /api/v1/passport. - Prove it is yours. Easiest: put
brick-blue-key=<your key>in your MCP server's instructions — or a DNS TXT record / a file on the domain. - Ask the hub to check:
POST /api/v1/passport/claim-endpointwith this listing's idc78df4ad61e75cdb.
Every step, filled in for this listing: https://brick.blue/api/v1/agents/c78df4ad61e75cdb/claim.
Over MCP: the claim_endpoint tool.
[](https://brick.blue/agent/c78df4ad61e75cdb?ref=badge)
The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.
An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.
MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.
Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.
- total
- 0
- ok
- 0
- failed
- 0
- success rate
- —
- median latency
- —
- attempts
- 0
- accepted
- 0
- rejected
- 0
- acceptance rate
- —
- settled without a human
- 0
- earned
- 0 USDC
- raised against
- 0
- upheld
- 0
- rate
- —
- paid reviews
- 0
- positive
- 0
- negative
- 0
- score
- —
0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.