Foundplay
Server Details
Search Foundplay's directory of browser games: AI-made games, mashups and fan ports of classics.
- Status
- Healthy
- Uptime
- 96.8% over 21 days
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusion or misselection. The tool's purpose is crystal clear from its name and description.
The single tool uses a clear verb_noun pattern (search_games) that is self-explanatory and follows a common convention. No inconsistencies exist because there are no other tools to compare.
A single tool for searching games is borderline thin. While the server's scope is narrow, a directory typically benefits from additional operations like get_game or list_genres, making this feel under-provisioned.
The search tool covers discovery and returns rich metadata, but there is no direct way to retrieve a specific game by ID, browse with pagination, or access creator profiles. Notable gaps exist for a game directory surface.
Available Tools
1 toolsearch_gamesSearch browser gamesARead-onlyIdempotentInspect
Searches the free browser games listed on Foundplay, made by independent creators, many of them with AI tools. Matches the query against each game's title, one-line description and genres. Returns each match's title, description, genres, whether it plays on phones, whether people can play it together, play and upvote counts, the creator's X handle when known, and a link to its Foundplay page. Read-only. With no query, returns the most played games.
| Name | Required | Description | Default |
|---|---|---|---|
| sort | No | popular (most played, the default), trending (last 48 hours) or new. | |
| genre | No | Only games in this genre. | |
| limit | No | How many games to return. Default 8. | |
| phone | No | true for games with touch controls that play on a phone. | |
| query | No | Words to match, such as 'zombie shooter', 'racing', 'puzzle' or 'cozy farm'. | |
| multiplayer | No | true for games people play together, online or on one screen. |
Output Schema
| Name | Required | Description |
|---|---|---|
| games | Yes | |
| lists | Yes | |
| total | Yes | How many games matched in all. |
| browseAll | Yes | Every game on Foundplay. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered; the description's 'Read-only' line is redundant with them. It does add real context by disclosing the matching fields and the fallback behavior when no query is supplied, which is beyond what annotations provide.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Purpose and matching semantics are front-loaded, and the sentence structure is clean. The long enumeration of returned fields is largely duplicated by the output schema and could be trimmed, which costs it a point.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given six optional parameters, full schema coverage, and an existing output schema, the description covers purpose, matching behavior, defaults and the no-query case. Nothing needed to invoke it correctly is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description still adds value by clarifying that the query matches title, one-line description and genres, and by naming the returned fields (phone support, multiplayer, play/upvote counts) that map to the boolean filters, going past the schema's field-level docs.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (searches) and resource (free browser games on Foundplay), plus the scope of the corpus and what the query is matched against (title, one-line description, genres). An agent knows exactly what this tool does without opening the schema.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explains that with no query it returns the most played games, which signals the default usage path, and the schema-level sort/limit options imply refinement. It stops short of explicit when-to-use vs alternatives, though there are no sibling tools to disambiguate against.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
- Changed
search_games1 field changed- changed
Output schema / (root)Previous value: -nullNew value: +{ + "properties": { + "browseAll": { + "description": "Every game on Foundplay.", + "type": "string" + }, + "games": { + "items": { + "properties": { + "creatorX": { + "description": "The creator's X handle, without @.", + "type": [ + "string", + "null" + ] + }, + "genres": { + "items": { + "type": "string" + }, + "type": "array" + }, + "multiplayer": { + "description": "true: people play it together. false: single-player. null: not known.", + "type": [ + "boolean", + "null" + ] + }, + "phoneFriendly": { + "description": "true: plays on phones. false: needs a keyboard. null: not known.", + "type": [ + "boolean", + "null" + ] + }, + "pitch": { + "description": "One line about the game.", + "type": "string" + }, + "plays": { + "type": "integer" + }, + "title": { + "type": "string" + }, + "type": { + "type": "string" + }, + "upvotes": { + "type": "integer" + }, + "url": { + "description": "The game's page on Foundplay, with a Play button.", + "type": "string" + } + }, + "required": [ + "title", + "pitch", + "url", + "type", + "genres", + "phoneFriendly", + "multiplayer", + "plays", + "upvotes", + "creatorX" + ], + "type": "object" + }, + "type": "array" + }, + "lists": { + "items": { + "properties": { + "title": { + "type": "string" + }, + "url": { + "type": "string" + } + }, + "required": [ + "title", + "url" + ], + "type": "object" + }, + "type": "array" + }, + "total": { + "description": "How many games matched in all.", + "type": "integer" + } + }, + "required": [ + "total", + "games", + "lists", + "browseAll" + ], + "type": "object" +}
1 tool update
- Changed
search_games1 field changed- changed
Input schema / properties / query / descriptionPrevious value: -"Words to match, such as 'halo', 'zombie shooter', 'mario kart' or 'cozy'."New value: +"Words to match, such as 'zombie shooter', 'racing', 'puzzle' or 'cozy farm'."
1 tool update
- Changed
search_games1 field changed- added
Input schema / properties / multiplayerAdded value: +{ + "description": "true for games people play together, online or on one screen.", + "type": "boolean" +}
1 tool update
- First observed
search_games
Related MCP Connectors
Search free AI-made browser games by genre, AI tool, engine, and multiplayer.
Search 101 free browser games + 1,000 Chrome Dino & gaming guides; returns dinogame.gg play links.
Find and play free games made by creators on Remix: puzzle, arcade, racing, sports and more.
- AsobiaiOAuthgames.asobiai
Publish AI-made browser games and get a shareable URL. Update, test and read player feedback.
Related MCP Servers
- AlicenseAqualityDmaintenanceSearch and explore 1,100+ games with 69-dimension Gameplay DNA profiles and find similar games via AI-powered cosine similarity.43 npmMIT
- FlicenseAqualityDmaintenanceProvides access to classic DOS games like DOOM, Super Mario, Tetris, and Duke Nukem 3D through js-dos emulation, allowing users to play these legendary games directly from their AI assistant.37 npm4-
- AlicenseNot gradedqualityFmaintenanceTurn the AI you already use into a game studio. Describe a game and Claude or Cursor builds it as a real 3D browser game: playable immediately, hosted on its own link, shareable with anyone. No engine, no build step, no code knowledge, nothing to export. Your AI ships the whole thing: it pulls free 3D assets, rigs characters, and playtests its own build until the game works. Free to start.MIT
- AlicenseAqualityBmaintenanceLet coding agents play, test and tune your 2D web game. The debuff MCP server attaches to the game you have open (or runs a headless copy) and gives agents live state, explained and source-mapped errors, frame timings, typed params, deterministic replays and rewind, scenario tests and fuzz playtesting. Everything an agent does shows in your dev panel, where you can undo it.213MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.