Steam MCP Server

Overview Schema Source Related Servers Discussions Admin

Get game reviews

get_game_reviews

Read-only

Fetches a game's review summary and sample reviews by appid, defaulting to the most helpful from the last 30 days. Filter by language or positive/negative, and adjust ordering or time window.

Instructions

Get the review summary (score label, positive/negative counts, %) and a few reviews for a game by appid — by default the most helpful ones posted in the last 30 days; set order for the newest or most recently edited instead, or within_days to widen/narrow the helpful window. Review text over 600 characters is truncated. An unknown appid comes back with a null summary and counts and no reviews rather than an error; confirm the appid with get_game if that matters. For long-term trend instead of a snapshot, use get_review_histogram. Get the appid from search_games. No API key required.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "appid": "<appid>"
    },
    "name": "get_game_reviews"
  }
}

Input Schema

Name	Required	Description	Default
`type`	No	Only positive or negative reviews. Default 'all'. Steam only computes the summary (score label, totals, %) for 'all' — filtering to positive/negative nulls those fields out, leaving only the review excerpts.	all
`appid`	Yes	Steam application id (appid). Get it from search_games.
`limit`	No	How many reviews (1-20). Default 5.
`order`	No	helpful (default) = most voted-helpful within within_days; recent = newest first; updated = most recently edited first. The summary counts are the same in every order.	helpful
`within_days`	No	order='helpful' only: how many past days the helpful ranking covers (1-365). Default 30 (Steam's own); 365 is Steam's ceiling — larger windows return the same reviews (verified live), so there is no all-time ranking. If the window holds no reviews, Steam widens it on its own.
`review_language`	No	Filter reviews by language. Use Steam's full language name — english, russian, schinese — NOT an ISO code like en/ru/zh: Steam answers an unrecognized value with zero reviews rather than an error, so a 9M-review game reads as having none. Default 'all'. Setting this ALSO rescopes the summary counts (total_reviews / positive / negative / %) to that language — they are no longer the game's global totals. Leave it at 'all' when you want those.	all

Output Schema

Name	Required	Description	Default
`reviews`	Yes
`summary`	Yes
`positive_pct`	Yes
`total_reviews`	Yes
`total_negative`	Yes
`total_positive`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.17.2Nov 6, 2026

changedInput schema / properties / within_days / description

Previous value: -"order='helpful' only: how many past days the helpful ranking covers (1-365). Default 30 (Steam's own); 365 is Steam's ceiling — larger windows return the same reviews (verified live), so there is no all-time ranking."New value: +"order='helpful' only: how many past days the helpful ranking covers (1-365). Default 30 (Steam's own); 365 is Steam's ceiling — larger windows return the same reviews (verified live), so there is no all-time ranking. If the window holds no reviews, Steam widens it on its own."

Changed3 schema fields changedv0.17.0Oct 25, 2026

changedInput schema / properties / limit / description

Previous value: -"How many recent reviews (1-20). Default 5."New value: +"How many reviews (1-20). Default 5."

addedInput schema / properties / order

Added value: +{
+  "default": "helpful",
+  "description": "helpful (default) = most voted-helpful within within_days; recent = newest first; updated = most recently edited first. The summary counts are the same in every order.",
+  "enum": [
+    "helpful",
+    "recent",
+    "updated"
+  ],
+  "type": "string"
+}

addedInput schema / properties / within_days

Added value: +{
+  "description": "order='helpful' only: how many past days the helpful ranking covers (1-365). Default 30 (Steam's own); 365 is Steam's ceiling — larger windows return the same reviews (verified live), so there is no all-time ranking.",
+  "exclusiveMinimum": 0,
+  "maximum": 365,
+  "type": "integer"
+}

Changed16 schema fields changedv0.14.0Sep 27, 2026
- removedOutput schema / properties / positive_pct / anyOf
```
Removed value: -[
-  {
-    "type": "number"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / positive_pct / type
```
Added value: +[
+  "number",
+  "null"
+]
```
- removedOutput schema / properties / reviews / items / properties / author_playtime_hours / anyOf
```
Removed value: -[
-  {
-    "type": "number"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / reviews / items / properties / author_playtime_hours / type
```
Added value: +[
+  "number",
+  "null"
+]
```
- removedOutput schema / properties / reviews / items / properties / text / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / reviews / items / properties / text / type
```
Added value: +[
+  "string",
+  "null"
+]
```
- removedOutput schema / properties / reviews / items / properties / voted_up / anyOf
```
Removed value: -[
-  {
-    "type": "boolean"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / reviews / items / properties / voted_up / type
```
Added value: +[
+  "boolean",
+  "null"
+]
```
- removedOutput schema / properties / summary / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / summary / type
```
Added value: +[
+  "string",
+  "null"
+]
```
- removedOutput schema / properties / total_negative / anyOf
```
Removed value: -[
-  {
-    "type": "number"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / total_negative / type
```
Added value: +[
+  "number",
+  "null"
+]
```
- removedOutput schema / properties / total_positive / anyOf
```
Removed value: -[
-  {
-    "type": "number"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / total_positive / type
```
Added value: +[
+  "number",
+  "null"
+]
```
- removedOutput schema / properties / total_reviews / anyOf
```
Removed value: -[
-  {
-    "type": "number"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / total_reviews / type
```
Added value: +[
+  "number",
+  "null"
+]
```

Changed2 schema fields changedv0.13.1Aug 17, 2026

changedInput schema / properties / review_language / description

Previous value: -"Filter reviews by language, e.g. 'english'. Default 'all'."New value: +"Filter reviews by language. Use Steam's full language name — english, russian, schinese — NOT an ISO code like en/ru/zh: Steam answers an unrecognized value with zero reviews rather than an error, so a 9M-review game reads as having none. Default 'all'. Setting this ALSO rescopes the summary counts (total_reviews / positive / negative / %) to that language — they are no longer the game's global totals. Leave it at 'all' when you want those."

addedInput schema / properties / review_language / minLength
```
Added value: +1
```

Changed6 schema fields changedv0.12.1Jul 30, 2026
- addedInput schema / additionalProperties
```
Added value: +false
```
- addedInput schema / properties / limit / default
```
Added value: +5
```
- addedInput schema / properties / limit / exclusiveMinimum
```
Added value: +0
```
- removedInput schema / properties / limit / minimum
```
Removed value: -1
```
- addedInput schema / properties / review_language / default
```
Added value: +"all"
```
- addedInput schema / properties / type / default
```
Added value: +"all"
```
Addedv0.10.2Jul 22, 2026
Removedv0.9.0Jul 18, 2026
Addedv0.8.0Jul 17, 2026
Removedv0.8.0Jul 17, 2026
First observedv0.1.0Jun 29, 2026

TDQS

A4.6/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well past the readOnly/openWorld annotations: discloses the 600-character text truncation, the null-summary-and-no-reviews behavior for an unknown appid instead of an error, the 30-day default helpful window, and that no API key is required. Missing only pagination/rate-limit detail, which matters little given a hard limit of 20 and an output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with what is returned and the default window; every subsequent sentence carries a distinct operational fact (truncation, null-not-error, sibling routing, appid source, no key). It runs long as a single block without formatting breaks, which slightly hurts scannability but not substance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A six-parameter read tool with an output schema and readOnly/openWorld annotations: the description covers return content, defaults, truncation, edge-case behavior on bad appid, sibling alternatives, and prerequisite lookup. Nothing an agent needs to invoke it correctly is absent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% so the baseline is 3, but the description adds cross-parameter meaning beyond the field docs: order='helpful' pairs with within_days, and within_days only widens/narrows the helpful window. It does not restate the important type/review_language caveats the schema already covers, which is fine.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Get the review summary ... and a few reviews for a game by appid') plus the exact return shape (score label, positive/negative counts, %). It explicitly distinguishes itself from get_review_histogram ('For long-term trend instead of a snapshot') so an agent can pick between the two without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Names both the alternative and the condition that selects it ('For long-term trend instead of a snapshot, use get_review_histogram'), routes appid lookup to search_games, and suggests get_game when appid validity matters. Defaults are also framed as usage decisions (order, within_days), leaving little to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.