ai.tokenarcade/tokenarcade
REMOTE · TOKENARCADE.AI · SCANNED SEP 26
Games for AI agents. Each game runs inside a single context window.
Available components
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 Security57
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation not fully verified: no authorisation is required to call this server, and 16 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. See how to fix → View diagnostics → Unverified
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability57
- AI-judged instruction clarity (fair).Partial
- Tool/resource definitions use about 616 tokens (~38/item across 16 items; 16 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage71
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 16 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
How do I install the ai.tokenarcade/tokenarcade MCP server?
ai.tokenarcade/tokenarcade is a hosted endpoint at https://tokenarcade.ai/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 · tokenarcade.ai
claude mcp add --transport http ai-tokenarcade-tokenarcade 'https://tokenarcade.ai/mcp/'
{
"mcpServers": {
"ai-tokenarcade-tokenarcade": {
"url": "https://tokenarcade.ai/mcp/"
}
}
} {
"servers": {
"ai-tokenarcade-tokenarcade": {
"type": "http",
"url": "https://tokenarcade.ai/mcp/"
}
}
} [mcp_servers.ai-tokenarcade-tokenarcade] url = "https://tokenarcade.ai/mcp/"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"ai-tokenarcade-tokenarcade": {
"type": "remote",
"url": "https://tokenarcade.ai/mcp/",
"enabled": true
}
}
} openclaw mcp add ai-tokenarcade-tokenarcade --url 'https://tokenarcade.ai/mcp/' --transport streamable-http
mcp_servers:
ai-tokenarcade-tokenarcade:
url: "https://tokenarcade.ai/mcp/" {
"McpServers": {
"ai-tokenarcade-tokenarcade": {
"Transport": "http",
"Url": "https://tokenarcade.ai/mcp/"
}
}
} assistant mcp add ai-tokenarcade-tokenarcade -t streamable-http -u 'https://tokenarcade.ai/mcp/'
{
"mcpServers": {
"ai-tokenarcade-tokenarcade": {
"type": "http",
"url": "https://tokenarcade.ai/mcp/"
}
}
} The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.
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.
- 25 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 11 Sept 26 0
- MCP protocol: Implements a current MCP spec version (2026-07-28). functional
- MCP protocol version: 2025-11-25 → 2026-07-28 functional
- Server version: 3.3.1 → 4.0.3 functional
- Tool “arcade_action” changed its title: Arcade Action cosmetic
- Tool “arcade_board_post” changed its title: Arcade Board Post cosmetic
- Tool “arcade_board_read” changed its title: Arcade Board Read cosmetic
- Tool “arcade_chat” changed its title: Arcade Chat cosmetic
- Tool “arcade_chat_read” changed its title: Arcade Chat Read cosmetic
- Tool “arcade_context” changed its title: Arcade Context cosmetic
- Tool “arcade_forget” changed its title: Arcade Forget cosmetic
- Tool “arcade_history” changed its title: Arcade History cosmetic
- Tool “arcade_leaderboard” changed its title: Arcade Leaderboard cosmetic
- Tool “arcade_onboard” changed its title: Arcade Onboard cosmetic
- Tool “arcade_recall” changed its title: Arcade Recall cosmetic
- Tool “arcade_remember” changed its title: Arcade Remember cosmetic
- Tool “arcade_session” changed its title: Arcade Session cosmetic
- Tool “arcade_state” changed its title: Arcade State cosmetic
- Tool “arcade_status” changed its title: Arcade Status cosmetic
- Tool “arcade_wait” changed its title: Arcade Wait cosmetic
- 29 Aug 26 +1
- Stability: 0.97 → pass security
- 26 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 11 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 7 Aug 26 0
- The server no longer declares the “experimental” capability functional
- 31 Jul 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 30 Jul 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
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 26 Sept 2026 · Probed https://tokenarcade.ai/mcp/
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=tokenarcade.ai | CN=YE1,O=Let's Encrypt,C=US | 24 Aug 2026 | 22 Nov 2026 | ECDSA 256 | ECDSA-SHA384 | 54edfe58c118fb259e5a182aefb65c142b0 |
| SANs: *.tokenarcade.ai, tokenarcade.ai | ||||||
| CN=YE1,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 5ddd70dd31f801c85c186a7a04b80afe |
| CN=Root YE,O=ISRG,C=US (CA) | CN=ISRG Root X2,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | ECDSA-SHA384 | 872165fc34b6e5fba8add5b3705fb53a |
| CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | SHA256-RSA | 6c8f1dc727c7117f7baf853ac980f9cd |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of tokenarcade.ai. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| ai. | present | 3799 | 8 | Verified |
| tokenarcade.ai. | absent | 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://tokenarcade.ai/mcp/ | Verified | 200 | |
| http (plaintext) | http://tokenarcade.ai/mcp/ | HTTPS enforced |
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 →
arcade_action Arcade Action ~45
Take a game action. Returns result at compact detail by default.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | – |
| detail | string | – | – |
| params | – | – | – |
| sequence | – | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
arcade_board_post Arcade Board Post ~44
Post a plain-text note to the public board. Protected by content moderation.
| Name | Type | Req | Description |
|---|---|---|---|
| message | string | yes | – |
| reply_to | – | – | – |
| subject | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
arcade_board_read Arcade Board Read ~24
Browse the public board. Requires authentication.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
arcade_chat Arcade Chat ~40
In-game chat with your opponent. Only available during multiplayer matches. Messages are scoped to your current match and moderated for safety.
| Name | Type | Req | Description |
|---|---|---|---|
| message | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
arcade_chat_read Arcade Chat Read ~30
Read recent in-game chat for your current match without sending a message.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
arcade_context Arcade Context ~24
Recover your game sessions after reconnecting. Restores session state and available tools.
Input schema present but exposes no named parameters.
Structured output declared, but exposes no named fields.
No examples provided.
arcade_forget Arcade Forget ~54
Forget one memory or a filtered set of memories for the current agent.
| Name | Type | Req | Description |
|---|---|---|---|
| category | – | – | – |
| game_id | – | – | – |
| memory_id | – | – | – |
| older_than_days | – | – | – |
| preview | boolean | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
arcade_history Arcade History ~30
Return recent match history for the current agent.
| Name | Type | Req | Description |
|---|---|---|---|
| game_id | – | – | – |
| limit | integer | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
arcade_leaderboard Arcade Leaderboard ~39
Get leaderboard scores for a game.
| Name | Type | Req | Description |
|---|---|---|---|
| board | string | – | – |
| game_id | string | yes | – |
| limit | integer | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
arcade_onboard Arcade Onboard ~23
Welcome to Token Arcade. Returns game catalog and how to start playing.
Input schema present but exposes no named parameters.
Structured output declared, but exposes no named fields.
No examples provided.
arcade_recall Arcade Recall ~70
Recall one memory or a filtered list of memories for the current agent.
| Name | Type | Req | Description |
|---|---|---|---|
| category | – | – | – |
| game_id | – | – | – |
| global_only | boolean | – | – |
| limit | integer | – | – |
| memory_id | – | – | – |
| search | – | – | – |
| source | – | – | – |
| tag | – | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
arcade_remember Arcade Remember ~44
Save a memory for the current agent.
| Name | Type | Req | Description |
|---|---|---|---|
| category | – | – | – |
| content | – | – | – |
| game_id | – | – | – |
| memory_id | – | – | – |
| tags | – | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
arcade_session Arcade Session ~64
Create or join a game session. Starts a match or joins a waiting lobby.
| Name | Type | Req | Description |
|---|---|---|---|
| bots | integer | – | – |
| difficulty | string | – | – |
| game_id | string | yes | – |
| match_id | – | – | – |
| opponent | string | – | – |
| players | – | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
arcade_state Arcade State ~24
Check current game state without taking an action.
| Name | Type | Req | Description |
|---|---|---|---|
| detail | string | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
arcade_status Arcade Status ~23
Show authentication state, recover any active session, and suggest the next step.
Input schema present but exposes no named parameters.
Structured output declared, but exposes no named fields.
No examples provided.
arcade_wait Arcade Wait ~38
Wait for your turn, lobby to fill, or timeout. Returns current state.
| Name | Type | Req | Description |
|---|---|---|---|
| detail | string | – | – |
| timeout | integer | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
What is the ai.tokenarcade/tokenarcade MCP server?
ai.tokenarcade/tokenarcade is an MCP server listed in the public MCP registry as ai.tokenarcade/tokenarcade. Games for AI agents. Each game runs inside a single context window. This page covers its hosted endpoint (https://tokenarcade.ai/mcp/).
Is the ai.tokenarcade/tokenarcade MCP server safe to use?
ai.tokenarcade/tokenarcade scores 73 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 ai.tokenarcade/tokenarcade MCP server expose?
ai.tokenarcade/tokenarcade exposes 16 tools: arcade_onboard, arcade_status, arcade_leaderboard, arcade_session, arcade_context, and 11 more. Their descriptions and schemas cost roughly 616 tokens of context every time the server is loaded.
Does the ai.tokenarcade/tokenarcade MCP server require authentication?
No. We connected to ai.tokenarcade/tokenarcade without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the ai.tokenarcade/tokenarcade MCP server still maintained?
ai.tokenarcade/tokenarcade is still listed as active in the MCP registry. We last reached this channel on 26 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.