# imho.run game recommendations (remote · imho.run)

Steam games like any game you name, facts about a game, and finding a game from a description.

- Trust score: 74/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-17

## Components

- remote · `imho.run`: 74/100 (this document), [markdown](https://verifymcp.io/servers/run-imho-games/imho.md), [page](https://verifymcp.io/servers/run-imho-games/imho)

## Channel facts

- Endpoint: `https://imho.run/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-17.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 64/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2099 tokens (~262/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 50/100
  - Stability observed for 15 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 91/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 69% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the imho.run game recommendations MCP server?

imho.run game recommendations is a hosted endpoint at https://imho.run/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http run-imho-games 'https://imho.run/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "run-imho-games": {
      "url": "https://imho.run/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "run-imho-games": {
      "type": "http",
      "url": "https://imho.run/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.run-imho-games]
url = "https://imho.run/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "run-imho-games": {
      "type": "remote",
      "url": "https://imho.run/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add run-imho-games --url 'https://imho.run/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  run-imho-games:
    url: "https://imho.run/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "run-imho-games": {
      "Transport": "http",
      "Url": "https://imho.run/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add run-imho-games -t streamable-http -u 'https://imho.run/mcp'
```

### Other

```json
{
  "mcpServers": {
    "run-imho-games": {
      "type": "http",
      "url": "https://imho.run/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-17 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-15 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-13 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-10 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-09 (score 70, −1)

- [functional regression] Tool coverage: 80% → 69%
- [functional regression] Schema quality: pass → fail
- [functional] First check of Tool coverage: 100

### 2026-10-04 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-03 (score 70, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-02 (score 70)

First indexed and scored.

## MCP tools (8)

### `games_like` (~263 tokens)

Games like X

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, price, Steam Deck status, year, review numbers, the imho.run page URL and the Steam URL. Use it for 'games like X', optionally only free, co-op or Steam Deck games. Use `recommend` instead when the user names 2-3 games, wants other filters (no PvP, no microtransactions, release years, niche) or describes what they want in words. Games rated for adults only (explicit sexual content) are not covered; filtering is best effort.

Input parameters:

- `coop` (boolean): Only co-op games.
- `coop_mode` (string): Kind of co-op (implies coop): online co-op (Remote Play Together does not count), or local same-screen / split-screen co-op.
- `free` (boolean): Only free games.
- `game` (string, required): Game name (typos and Russian names are fine), Steam appid or Steam store URL.
- `lang` (string): Language of the `why` lines.
- `n` (integer)
- `steam_deck` (string): Steam Deck verified, or playable-or-better.

Output parameters:

- `attribution` (string)
- `filters` (object)
- `generated_at` (string)
- `lang` (string)
- `list_url` (string): The same list on imho.run.
- `other_matches` (array): Other games the query could mean; pass one's appid as `q` to switch.
- `query` (string)
- `results` (array)
- `seed` (object)
- `source` (string): Always "imho.run".

### `recommend` (~437 tokens)

Recommend Steam games

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 and filters. Use it instead of games_like when the user names several games, wants filters beyond free / co-op / Steam Deck (no PvP, no microtransactions, no grind, not too hard, no Early Access, release years, more niche or more popular), or says what they want in words: pass that as `preferences` ('cozy base building, no combat'); the result says which Steam tags it was read as. When the user reacts to the picks, call it again with `liked` / `disliked`: liked games join the seeds, disliked ones never come back. Each pick has a one-line reason naming the seed it is closest to (`similar_to`), price, Steam Deck status, year, reviews, the imho.run URL and the Steam URL, plus `tool_url` (these games in imho.run's tool). Not for naming a game from a description (find_game_by_description) or facts about one game (game_facts). Games rated for adults only (explicit sexual content) are not covered; filtering is best effort.

Input parameters:

- `disliked` (array): Games the user disliked or already played: never recommended. Pass earlier picks the user rejected to get fresh ones.
- `filters` (object): All optional. Leave out what the user did not ask for.
- `lang` (string): Language of the `why` lines.
- `liked` (array): Other games the user said they liked (e.g. from earlier answers). They fill free seed slots after `seeds` (3 in all); the rest are listed in `ignored`.
- `n` (integer)
- `preferences` (string): What the user wants or wants to avoid, in their words (any language), e.g. 'dragons and crafting, no horror, no grind'. Read as Steam tags.
- `seeds` (array, required): 1-3 games the user likes: names, Steam appids or Steam URLs.

Output parameters:

- `attribution` (string)
- `filters` (object)
- `generated_at` (string)
- `ignored` (array): liked / disliked games not used: no match, or liked past the 3 seed slots.
- `lang` (string)
- `preferences`: How `preferences` were read as Steam tags.
- `preferences_applied`: null without `preferences`; false when they could not be read.
- `preferred_tags` (array)
- `query` (object)
- `results` (array)
- `seeds` (array)
- `source` (string)
- `tool_url` (string): imho.run's tool with these games picked; the user can tune filters there.

### `library_recs` (~228 tokens)

Recommendations from a Steam library

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; owned games are left out. Use it when the user gives their Steam profile and wants picks for their taste in general; for 'games like X' use games_like or recommend. Takes a SteamID64 or a steamcommunity.com/profiles/<SteamID64> link (not a custom /id/ name) and works only for public profiles imho.run already has; otherwise it returns one 'unavailable' error with a link the user can open to paste their profile. Each pick names the most-played game it is closest to (`similar_to`). Games rated for adults only (explicit sexual content) are not covered; filtering is best effort.

Input parameters:

- `filters` (object): All optional, same meaning as in recommend.
- `lang` (string): Language of the `why` lines.
- `n` (integer)
- `profile` (string, required): SteamID64 or steamcommunity.com/profiles/<SteamID64> link.

Output parameters:

- `attribution` (string)
- `based_on` (array): The profile's most-played games the reasons refer to.
- `filters` (object)
- `generated_at` (string)
- `lang` (string)
- `results` (array)
- `source` (string)
- `tool_url` (string): imho.run's library mode, where the user can paste the link.

### `game_facts` (~147 tokens)

Game facts

Public facts about one Steam game: year, developers, genres, top tags, price, Steam Deck status, review numbers, a review-mined summary and links. For a few single-player games, `coop_via_mod` names a reviewed fan mod for co-op, with caveats. Use it to answer questions about a game the user names; for similar games use games_like or recommend. Games rated for adults only (explicit sexual content) are not covered; filtering is best effort.

Input parameters:

- `game` (string, required): Game name (typos and Russian names are fine), Steam appid or Steam store URL.
- `lang` (string): Language of the `why` lines.

Output parameters:

- `attribution` (string)
- `game` (object)
- `generated_at` (string)
- `lang` (string)
- `other_matches` (array)
- `query` (string)
- `source` (string)

### `find_game_by_description` (~300 tokens)

Find a 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 `confidence`, and `find_game_url`: imho.run's /find-game page with the description filled in (the user presses the button; nothing runs by itself). Pass what the user said about the platform, the release years and the camera as `platform`, `year_min` / `year_max` and `perspective` instead of leaving them only in the text. When `confidence` is not high or no result fits, give the user `find_game_url` so they can add details there. Slow (LLM) and rate-limited: use it only when the user does not know the title; for games similar to a known game use games_like or recommend. Games rated for adults only (explicit sexual content) are not covered; filtering is best effort.

Input parameters:

- `description` (string, required): What the user remembers about the game, in their words.
- `lang` (string)
- `perspective` (string): Camera: first person, third person, top-down or side view.
- `platform` (string): Where the user played it, if they said (a platform family).
- `year_max` (integer): Latest plausible release year, if the user gave an era.
- `year_min` (integer): Earliest plausible release year, if the user gave an era.

Output parameters:

- `attribution` (string)
- `confidence`
- `find_game_url`: /find-game with the description filled in, for the user to refine.
- `lang` (string)
- `results` (array)
- `source` (string)
- `tool_url` (string)

### `trending` (~142 tokens)

Trending on Steam

Steam games trending right now (imho.run/trending): `rising` = established games gaining reviews and players against their own recent baseline, `breakouts` = new games taking off. Each has reviews this week, growth in %, price, Steam Deck status and links. Use it for 'what's hot / popular right now on Steam'; for new releases use new_releases, for games like a given game use games_like. Games rated for adults only (explicit sexual content) are not covered; filtering is best effort.

Input parameters:

- `kind` (string)
- `lang` (string): Language of the `why` lines.
- `n` (integer)

Output parameters:

- `attribution` (string)
- `kind` (string)
- `lang` (string)
- `page_url` (string)
- `results` (array)
- `source` (string)
- `status` (string): collecting: the lists are not ready yet; results is empty.
- `updated_at`

### `new_releases` (~244 tokens)

New Steam releases

Games released on Steam in the last 30 days that players rate well (70%+ positive, 50+ positive reviews), or with `upcoming` the upcoming games that have a release date; optionally co-op only. The site's New releases list, with price, Steam Deck status, release date and links. Released games carry `release_kind`: `new`, or `ea_exit` for a game that just left Early Access (its 1.0; it was playable before), so call those 'out of Early Access', not new. `ea_exits`: include (default), exclude (brand-new games only) or only. Use it for 'what's new / coming out'; for what is gaining players now use trending. Games rated for adults only (explicit sexual content) are not covered; filtering is best effort.

Input parameters:

- `coop` (boolean)
- `ea_exits` (string): Games that just left Early Access: include them, exclude them (only brand-new launches) or return only them.
- `lang` (string): Language of the `why` lines.
- `n` (integer)
- `upcoming` (boolean)

Output parameters:

- `attribution` (string)
- `coop` (boolean)
- `ea_exits` (string): The Early Access exits filter this list was built with.
- `kind` (string)
- `lang` (string)
- `page_url` (string)
- `results` (array)
- `source` (string)

### `search_games` (~116 tokens)

Search Steam games by title

Find Steam games by title (typos, partial names, Russian names and acronyms are fine): appid, year, imho.run page and Steam link for each match. Use it to check which game the user means or to get an appid; the other tools also accept names directly. For a game the user can only describe, use find_game_by_description. Games rated for adults only (explicit sexual content) are not covered; filtering is best effort.

Input parameters:

- `n` (integer)
- `query` (string, required)

Output parameters:

- `query` (string)
- `results` (array)
- `source` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/run-imho-games/imho#diagnostics

## Score history

- 2026-10-17: 74
- 2026-10-16: 73
- 2026-10-15: 73
- 2026-10-14: 72
- 2026-10-13: 72
- 2026-10-12: 71
- 2026-10-10: 71
- 2026-10-09: 70
- 2026-10-04: 71
- 2026-10-03: 70
- 2026-10-02: 70

## Common questions

### What is the imho.run game recommendations MCP server?

imho.run game recommendations is an MCP server listed in the public MCP registry as run.imho/games. Steam games like any game you name, facts about a game, and finding a game from a description. This page covers its hosted endpoint (https://imho.run/mcp).

### Is the imho.run game recommendations MCP server safe to use?

imho.run game recommendations scores 74 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the imho.run game recommendations MCP server expose?

imho.run game recommendations exposes 8 tools: games_like, recommend, library_recs, game_facts, find_game_by_description, and 3 more. Their descriptions and schemas cost roughly 1,877 tokens of context every time the server is loaded.

### Does the imho.run game recommendations MCP server require authentication?

No. We connected to imho.run game recommendations without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the imho.run game recommendations MCP server still maintained?

imho.run game recommendations is still listed as active in the MCP registry. We last reached this channel on 17 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://imho.run/mcp
- Website: https://imho.run/developers
- Changelog RSS feed: https://verifymcp.io/servers/run-imho-games/imho.xml
- Changelog JSON feed: https://verifymcp.io/servers/run-imho-games/imho.json
- HTML version of this page: https://verifymcp.io/servers/run-imho-games/imho