Borrowing it
Nothing to install: this file belongs to fenxer/steam-review-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/fenxer/steam-review-mcp/main/.cursor/skills/steam-review-mcp/SKILL.mdgit clone --depth 1 https://github.com/fenxer/steam-review-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/fenxer/steam-review-mcp/steam-review-mcp)<a href="https://agentmods.dev/skills/fenxer/steam-review-mcp/steam-review-mcp"><img src="https://agentmods.dev/badge/skills/fenxer/steam-review-mcp/steam-review-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/fenxer/steam-review-mcp/steam-review-mcp"><img src="https://agentmods.dev/badge/skills/fenxer/steam-review-mcp/steam-review-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00074 | $0.00978 |
| Opus 5.5 | $0.00030 | $0.00391 |
| Sonnet 5.5 | $0.00015 | $0.00196 |
| Haiku 4.5 | $0.00007 | $0.00098 |
Grade A, and why
steam-review-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Steam Review MCP
store.steampowered.com/appreviews/<appid> was disabled on 2026-10-22. store.steampowered.com/api/appdetails is not the store source for this server. Call the service methods below. A Web API key is optional.
Tools
Use get_steam_review for one page of reviews plus the store name and description. Pass string enums; the server maps them into input_json.
| Tool argument | Steam input_json |
|---|---|
filter=all |
filter: 0 (Helpful). Also recent: 1, updated: 2, funny: 3. |
language=schinese |
languages: ["schinese"]. all means every language. Omitting the list would mean English only, so always send the argument. |
review_type=all |
review_type: 0. Score fields are omitted unless this is all and the page is the first page. positive: 1, negative: 2. |
purchase_type=steam |
purchase_type: 0 (default). all: 1. non_steam_purchase: 2. |
day_range |
Helpful filter only. 0 means no limit. Maximum 365. |
cursor |
* on the first page, then the returned cursor. Do not URL-encode it yourself. |
num_per_page |
1–100. 0 omits query_summary; do not send it. |
Review endpoint:
GET https://api.steampowered.com/IUserReviewsService/GetAppReviews/v1/?input_json=...
Store endpoint, one known App ID only:
GET https://api.steampowered.com/IStoreBrowseService/GetItems/v1/?input_json=...
Read STEAM_WEB_API_KEY from the environment when a higher rate limit is needed. Never log it, and do not put it in source. A missing key is not a failure. HTTP 429 is a stop, not a cue to retry in a loop.
The response has no success field. HTTP 200 with a response object is success. An empty response means no matching reviews: keep null aggregates and an empty reviews array. Do not invent zeros.
get_steam_review returns cleaned review text. That is intentional for this tool. Do not also store author SteamIDs, vote records, or the raw review objects. Pass cursor to the next call when another page is required. total_matching is the filtered total. total_reviews is the score denominator and does not follow day_range.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 57 lines · 74 tokens per session scan A a52c1b538f8d
steam-review-mcp is a skill published in the GitHub repository fenxer/steam-review-mcp (7 stars, last pushed 6d ago), licensed MIT. It adds 74 tokens to every session and 978 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-27.
steam-review-mcp compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| steam-review-mcpfenxer/steam-review-mcp | Skill | 7 | 6d ago | MIT | A | 74 | Cursor |
| gamedev-shippingericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 99 | Claude Code, Codex |
| steam-mcpsandraschi/steam-mcp | Skill | 3 | today | MIT | A | 0 | Claude Code, Codex |
| unreal-multiplayerbuiphucminhtam/forgewright | Skill | 49 | 6d ago | none | A | 45 | Claude Code |
| playtest-reportDonchitos/Claude-Code-Game-Studios | Skill | 36k | 18d ago | MIT | A | 20 | Claude Code |
| godot-signals-groupsgamedev-skills/awesome-gamedev-agent-skills | Skill | 6.9k | 9d ago | Apache-2.0 | A | 95 | Claude Code |
| scenario-unreal-gameplayscenario-labs/skills | Skill | 3.2k | yesterday | MIT | A | 121 | Claude Code |