Skip to main content
Glama
Social Fetch MCP

Social Fetch MCP

Official

Search Steam store

steam_apps_search
Read-onlyIdempotent

Search the Steam store by keyword and filter by tags, price, platform, language, developer, or publisher to find matching games, software, DLC, and other items.

Instructions

Search the Steam store by keyword with tag, price, platform and language filters. Optional inputs: query, category, tags, developer, publisher and 9 more. Returns a list (use page when paginated).

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": {
      "context": "<context>",
      "llm_model": "<llm_model>"
    },
    "name": "steam_apps_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
osNoOnly apps that run on this operating system.
pageNoPage number (1-based). Default: 1.
sortNo`relevance` (default) is Steam's ranking and can reorder between requests, so a walk can repeat rows across pages. `released` (newest first) and `name` (A to Z) are stable; the others are as named.
tagsNoOnly apps with all of these tag ids, comma-separated, e.g. `1684,19`. Tag ids are in the tags endpoint.
limitNoResults per page, 1 to 100. Default: 25.
queryNoWords to search the store for, e.g. `portal`.
onSaleNoOnly apps with a discount right now.
contextYesDescribe the user's underlying goal in one sentence, not the tool you are calling.
countryNoCountry the prices are shown for, as an ISO 3166-1 alpha-2 code. Default: `US`.
categoryNoOnly this kind of item. Without it, search covers everything.
languageNoLanguage of the text: a Steam language name or short code such as `german` or `de`. Default: `en`.
maxPriceNoHighest price in whole currency units, e.g. `10`, or `free` for free apps only.
developerNoOnly apps by this developer, by name.
llm_modelYesThe exact model identifier you (the assistant) are running as, taken from your system prompt or environment (for example "claude-opus-4-8" or "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" and do not guess.
publisherNoOnly apps by this publisher, by name.
conversation_idNoEcho the conversation_id from the server's previous response. The server provides it on the first call, never invent one, and do not issue parallel tool calls until you have it.
supportedLanguageNoOnly apps with this language supported, as a short code such as `de`.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare read-only, idempotent, open-world, non-destructive, so safety needs no restating. The description adds only that results are a list and 'use page when paginated', missing richer behavior such as how relevance sorting destabilizes paging across requests — a point that lives only in the 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?

Two short sentences, with the core action front-loaded and no marketing filler. The '9 more' and the parenthetical about paging are slightly vague but not wasteful.

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

Completeness3/5

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

For a 17-parameter search with no output schema, the description is minimal: it never characterizes the returned records, pagination interplay with sort, or the contract-style params (context, conversation_id) that matter for correct invocation. Annotations carry part of the load, but the definition leaves real gaps for a tool of this complexity.

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

Parameters3/5

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

Schema description coverage is 100%, so all 17 parameters including context, llm_model, conversation_id, sort and paging limits are already documented at the field level. The description merely names a subset of the optional inputs without adding format, defaults, or constraints, leaving it at the baseline.

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

Purpose4/5

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

States a specific verb and resource ('Search the Steam store by keyword') plus the filter families, which is clear. It does not, however, distinguish itself from likely siblings such as steam_apps_browse or steam_apps_suggest, so an agent can't tell from the text which one to pick.

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

Usage Guidelines3/5

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

Usage is only implied by 'by keyword' — the reader infers this is the tool for text-driven store lookups. There is no explicit when-to-use versus steam_apps_browse (browse without query) or steam_apps_suggest, and no stated exclusions or prerequisites.

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

Deploy Server

Other Tools