Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Playtable

REMOTE · PLAY.ROWHOUSESOFTWARE.COM

Make up any game and play it in chat: a fair table that deals, hides cards and rolls dice.

+3 this week 63 Trust /100

Last scanned (12 hours ago)

Scores higher than 45% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Entertainment and Games

Recent critical change

Authorization (12 Nov 2026). See the changelog before you install this server.

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security46
Transport & Reachability100
Schema Quality & AI Usability69
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1251 tokens (~208/item across 6 items; 5 tools + 1 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management40
  • Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage84
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 52% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
  • Supports UI / widget rendering.Pass
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol
  • Capabilities

Checks we could not complete (1)

These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • HTTPS in Endpoint SecurityHTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Nov 26 −6
    • Authorization: partial → fail ▼ critical
    • New tool “delete_game”, which the server declares destructive security
    • Schema quality: 1131 → 1251 ▼ functional
    • Destructive annotations: pass → 100 functional
  • 10 Nov 26 +1
    • Stability: unverified → 0.03 ▲ functional
  • 9 Nov 26 64

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://play.rowhousesoftware.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=rowhousesoftware.com CN=WE1,O=Google Trust Services,C=US 9 Nov 2026 7 Feb 2027 ECDSA 256 ECDSA-SHA256 98eca9b34ac0812e0e50894e9f605669
SANs: rowhousesoftware.com, play.rowhousesoftware.com, *.play.rowhousesoftware.com
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of play.rowhousesoftware.com. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
rowhousesoftware.com. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://play.rowhousesoftware.com/mcp Verified 200
http (plaintext) http://play.rowhousesoftware.com/mcp Inconclusive 405
MCP tools · 5 exposed · ~1,071 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
create_game ~439

Set up any game to play in this chat: board games, card games, dice games, word and guessing games, mysteries. Describe it with the building blocks below, or pass starter for a ready one (tic-tac-toe, four-in-a-row, gomoku, checkers, reversi, crazy-eights, go-fish, twenty-one, pig, sea-battle, hangman, twenty-questions). The server keeps the board, deals and hides cards, rolls dice and enforces turns, so the player can trust the game. The player gets an interactive board in the chat (and a link to play in a browser or invite friends). Returns game_id and agent_key; keep both for get_state and take_turn. You run the rules that aren't built in.

NameTypeReqDescription
aboutstring–The rules in a few sentences, shown to the player. Write them so you can follow them too.
boardobject––
countersarray–Scores and tallies: "score", or {name, per_seat: false, start}.
dealinteger–Cards dealt to each hand at the start.
deck––"standard" (52, ids like AS, 10H, QC), "standard_jokers", "numbers:1-10x4", or a list of card labels or {label, suit, rank}. Adds a face-down deck, a face-up table and a hidden hand per seat.
diceinteger–Default die sides.
firststring–Seat name that goes first.
piecesarray–Starting pieces.
pilesarray––
rulesobject–Rules the server enforces for you.
seatsarray–Players in turn order. Default: Player (human) then Agent (agent).
starterstring–A ready-made game. Other fields here override its setup (for example seats).
titlestring––
turnsstring–alternate (default): one seat at a time. free: anyone acts anytime (guessing games, puzzles).

No output schema declared.

No examples provided.

delete_game ~120

Delete a game for good: the board, cards, log, secrets, seats and keys, and Playtable's record of it. Its link stops working. Only call this when the player asks. It needs the delete_code from the board in the chat where the game was made; you never get that code yourself, so ask the player to paste it. With a wrong code nothing is deleted. This can't be undone.

NameTypeReqDescription
delete_codestringyesStarts with del_. The player copies it from the board.
game_idstringyes–

No output schema declared.

No examples provided.

get_state ~85

What your seat can see now: the board, your hand, public piles, scores, dice, secrets you hold and the recent log. Call it when the player says they've moved or it might be your turn.

NameTypeReqDescription
agent_keystringyes–
asstring–Which of your seats, when you play more than one.
game_idstringyes–

No output schema declared.

No examples provided.

show_board ~48

Show the interactive board in the chat again, for example after a long conversation or when the player asks to see it.

NameTypeReqDescription
agent_keystringyes–
game_idstringyes–

No output schema declared.

No examples provided.

take_turn ~379

Apply one or more actions for your seat, all or nothing: if any action is illegal, none happen and you get the reason. Usually end with end_turn. Action types and fields: - place {at: "B3"} or {column: "D"} with gravity; optional label, shape (disc, square, ring, star, diamond), color, kind, owner - move {from: "B3", to: "C4"} or {piece, to}; moving onto another player's piece takes it; optional label, kind - edit {at, owner?, label?, kind?, shape?, color?}: change a piece in place (flip, crown) - remove {at} or {piece} - mark {at, color?, label?}: paint or label a cell (hits, misses, letters) - draw {from?: "deck", to?: "hand", count?} - play {card, to?: "table", from?}: a card you can see, by id or label - give {card, to: seat} - shuffle {pile?}, collect {into?: "deck", from?: [piles]}: gather and reshuffle - roll {dice?: "2d6"}, pick {options: [...]}: server randomness, logged - score {counter?, seat?, add? | set?} - secret {name, value}: lock in hidden info (the word, the culprit, your fleet); reveal {name} - say {text}, end_turn {next?}, end_game {winner?, reason}, concede Cells are column letter + row number from the top: A1 is the top left.

NameTypeReqDescription
actionsarrayyes–
agent_keystringyes–
asstring––
game_idstringyes–

No output schema declared.

No examples provided.

Install

How do I install the Playtable MCP server?

Playtable is a hosted endpoint at https://play.rowhousesoftware.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · play.rowhousesoftware.com

# add to Claude Code
claude mcp add --transport http com-rowhousesoftware-playtable 'https://play.rowhousesoftware.com/mcp'
Common questions

What is the Playtable MCP server?

Playtable is an MCP server listed in the public MCP registry as com.rowhousesoftware/playtable. Make up any game and play it in chat: a fair table that deals, hides cards and rolls dice. This page covers its hosted endpoint (https://play.rowhousesoftware.com/mcp).

Is the Playtable MCP server safe to use?

Playtable scores 63 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Playtable MCP server expose?

Playtable exposes 5 tools: create_game, get_state, take_turn, show_board, delete_game. Their descriptions and schemas cost roughly 1,071 tokens of context every time the server is loaded.

Does the Playtable MCP server require authentication?

No. We connected to Playtable without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Playtable MCP server still maintained?

Playtable is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the Playtable MCP server?

VerifyMCP ran 13 checks on Playtable, covering TLS certificate, Authorization, HSTS header, DNSSEC and 9 more. One item could not be completed, a gap on our side rather than a finding about Playtable: HTTPS. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.