Skip to main content
Glama
icue

Steam Review and Forum MCP

by icue

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
STEAM_FORUM_EXPORT_DIRNoDirectory to store saved forum thread datasets. Defaults to a package-relative directory..steam-forum-exports/
STEAM_REVIEW_EXPORT_DIRNoDirectory to store saved review datasets. Defaults to a package-relative directory..steam-review-exports/
STEAM_FORUM_EXPORT_TTL_HOURSNoTime-to-live in hours for stored forum exports. Exports older than this are cleaned up.24
STEAM_REVIEW_EXPORT_TTL_HOURSNoTime-to-live in hours for stored review exports. Exports older than this are cleaned up.24

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
get_server_infoA

Returns the name and package version of the running MCP server process.

get_steam_reviewB

Retrieves Steam reviews for a specific app. Supports manual cursor pagination and automatic multi-page collection. Off-topic review activity is included by default. The response always includes a cleaned reviews text array, and can optionally include review_details with timestamps and playtime metadata when include_review_metadata is true.

get_steam_game_infoB

Retrieves English game metadata for a specific app, including release date, developers, publishers, genres, and price overview. The detailed description is cleaned into plain text for LLM consumption.

list_steam_forum_sectionsB

Lists the available public Steam Community discussion sections and forum-like app hub surfaces for a game's hub, including each section's numeric id when applicable and URL.

list_steam_forum_topicsA

Lists topics from a game's public Steam Community discussion section or compatible app hub forum surface. Supports section selection for discussions and listing pagination via ?fp=N. Each topic's last_activity_timestamp and last_activity_display describe its latest reply or listing activity, never its original publication time. Call get_steam_forum_topic and use topic.original_post_timestamp before making publication-date claims. On some app hub surfaces such as Events & Announcements, Steam omits row-level author and preview markup, so those fields may be null in listing results.

get_steam_forum_topicA

Fetches a public Steam Community topic, including the original post and replies. The returned topic.original_post_timestamp is the original topic or hydrated announcement publication time; reply items keep their own timestamp fields. Use this field, not listing activity, for publication-date claims. Supports General Discussions topics and compatible app hub forum surfaces such as Events & Announcements, with reply pagination via ?ctp=N. When an Events & Announcements thread only contains a stub that links to the real announcement article, the server follows that link and returns the announcement body and publication time when possible.

create_steam_forum_topic_corpusA

Starts a server-side background fetch for a public Steam Community topic, stores replies in server-managed chunks, and returns an opaque identifier immediately for later status checks and chunk reads. Supports discussion topics and compatible app hub forum surfaces. When an Events & Announcements thread only contains a stub that links to the real announcement article, the server follows that link and stores the announcement body as the topic content when possible. Data stays on the server and is not exported to the caller as files.

get_steam_forum_topic_corpus_statusB

Returns the persisted manifest and progress summary for a server-side Steam Community topic fetch.

read_steam_forum_topic_corpus_chunkC

Reads one stored reply chunk from a previously created server-side Steam Community topic fetch.

create_steam_review_corpusA

Starts a server-side background review fetch, stores results in a server-managed corpus, and returns an opaque identifier immediately for later status checks, server-side queries, and aggregates. Data stays on the server and is not exported to the caller as files. Stored review records keep per-review metadata such as timestamps and playtime fields by default.

get_steam_review_corpus_statusC

Returns the persisted manifest and progress summary for a server-side Steam review fetch.

query_steam_review_corpusB

Queries a stored Steam review corpus with server-side filtering, pagination, and optional field selection. Use it to retrieve only the subset of reviews you actually need for analysis. Date, sentiment, and playtime threshold filters require a corpus created with review metadata enabled.

aggregate_steam_review_corpusB

Aggregates a stored Steam review corpus server-side. Supports overall counts, positive versus negative review breakdowns, monthly or weekly trend buckets, average playtime, playtime-threshold filtered counts, and language breakdowns. Requires a corpus created with review metadata enabled.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.7/5.0

Scored across 13 tools

Disambiguation4/5

Tools are mostly distinct by resource and action (reviews vs forums, direct fetch vs corpus operations), so an agent can usually tell them apart. However, get_steam_review overlaps conceptually with the review corpus tools, and get_steam_forum_topic overlaps with the forum topic corpus tools, creating minor selection ambiguity.

Naming Consistency5/5

All tool names use consistent snake_case with predictable verb prefixes such as get_, list_, create_, read_, query_, and aggregate_. The only mild outlier is get_server_info, which omits the Steam-specific 'steam' token, but it still follows the same verb_noun convention.

Tool Count5/5

With 13 tools, the set is well-scoped for covering Steam reviews and forum data, including direct retrieval and corpus-based analysis. Each tool appears to serve a clear purpose without excessive duplication.

Completeness4/5

The surface covers core read and analysis workflows: direct review/forum retrieval, corpus creation, status, querying, aggregation, and chunk reading. Minor gaps exist, such as no corpus listing/deletion or forum search tool, but agents can still accomplish the primary Steam review and forum analysis tasks.

Maintenance

ActivityStale
ResponsivenessUnresponsive