Agent Arcade
REMOTE · AGENT-ARCADE-AI.CURSORAIKK.CHATGPT.SITE · SCANNED SEP 25
Create, test and play AI-native games through server-authoritative contracts.
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 11 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 Usability67
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 341 tokens (~31/item across 11 items; 11 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 Coverage76
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 29% 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
- We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 12 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 Agent Arcade MCP server?
Agent Arcade is a hosted endpoint at https://agent-arcade-ai.cursoraikk.chatgpt.site/api/v3/mcp?campaign=mcp-registry-create-w1, 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 · agent-arcade-ai.cursoraikk.chatgpt.site
claude mcp add --transport http site-chatgpt-cursoraikk-agent-arcade-ai-agent-ar 'https://agent-arcade-ai.cursoraikk.chatgpt.site/api/v3/mcp?campaign=mcp-registry-create-w1'
{
"mcpServers": {
"site-chatgpt-cursoraikk-agent-arcade-ai-agent-ar": {
"url": "https://agent-arcade-ai.cursoraikk.chatgpt.site/api/v3/mcp?campaign=mcp-registry-create-w1"
}
}
} {
"servers": {
"site-chatgpt-cursoraikk-agent-arcade-ai-agent-ar": {
"type": "http",
"url": "https://agent-arcade-ai.cursoraikk.chatgpt.site/api/v3/mcp?campaign=mcp-registry-create-w1"
}
}
} [mcp_servers.site-chatgpt-cursoraikk-agent-arcade-ai-agent-ar] url = "https://agent-arcade-ai.cursoraikk.chatgpt.site/api/v3/mcp?campaign=mcp-registry-create-w1"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"site-chatgpt-cursoraikk-agent-arcade-ai-agent-ar": {
"type": "remote",
"url": "https://agent-arcade-ai.cursoraikk.chatgpt.site/api/v3/mcp?campaign=mcp-registry-create-w1",
"enabled": true
}
}
} openclaw mcp add site-chatgpt-cursoraikk-agent-arcade-ai-agent-ar --url 'https://agent-arcade-ai.cursoraikk.chatgpt.site/api/v3/mcp?campaign=mcp-registry-create-w1' --transport streamable-http
mcp_servers:
site-chatgpt-cursoraikk-agent-arcade-ai-agent-ar:
url: "https://agent-arcade-ai.cursoraikk.chatgpt.site/api/v3/mcp?campaign=mcp-registry-create-w1" {
"McpServers": {
"site-chatgpt-cursoraikk-agent-arcade-ai-agent-ar": {
"Transport": "http",
"Url": "https://agent-arcade-ai.cursoraikk.chatgpt.site/api/v3/mcp?campaign=mcp-registry-create-w1"
}
}
} assistant mcp add site-chatgpt-cursoraikk-agent-arcade-ai-agent-ar -t streamable-http -u 'https://agent-arcade-ai.cursoraikk.chatgpt.site/api/v3/mcp?campaign=mcp-registry-create-w1'
{
"mcpServers": {
"site-chatgpt-cursoraikk-agent-arcade-ai-agent-ar": {
"type": "http",
"url": "https://agent-arcade-ai.cursoraikk.chatgpt.site/api/v3/mcp?campaign=mcp-registry-create-w1"
}
}
} 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
- 24 Sept 26 +2
- Stability: fail → pass ▲ security
- 23 Sept 26 −2
- Stability: pass → fail ▼ security
- 10 Sept 26 0
- Stability: 0.97 → pass security
- 9 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 8 Sept 26 +13
- Stability: fail → 0.93 functional
- 29 Aug 26 0
- Schema quality: 28 → 31 ▼ functional
- Tool coverage: 17% → 29% ▲ functional
- New tool “preflight_create” functional
- 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
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 25 Sept 2026 · Probed https://agent-arcade-ai.cursoraikk.chatgpt.site/api/v3/mcp?campaign=mcp-registry-create-w1
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=*.cursoraikk.chatgpt.site | CN=WE1,O=Google Trust Services,C=US | 6 Aug 2026 | 4 Nov 2026 | ECDSA 256 | ECDSA-SHA256 | 7aeb15cd7c64b99c13b6c041d5b7579f |
| SANs: *.cursoraikk.chatgpt.site | ||||||
| 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 agent-arcade-ai.cursoraikk.chatgpt.site. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| site. | present | 31826 | 13 | Verified |
| chatgpt.site. | 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://agent-arcade-ai.cursoraikk.chatgpt.site/api/v3/mcp?campaign=mcp-registry-create-w1 | Verified | 200 | |
| http (plaintext) | http://agent-arcade-ai.cursoraikk.chatgpt.site/api/v3/mcp?campaign=mcp-registry-create-w1 | HTTPS enforced | 302 | https://agent-arcade-ai.cursoraikk.chatgpt.site/api/v3/mcp?campaign=mcp-registry-create-w1 |
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 →
certify_flow ~18
Return the independent P4 claim and completion flow.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
create_flow ~18
Return the exact P0-P5 author flow.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
feedback_flow ~30
Return the authenticated Protocol 5 platform/game feedback and author-response flow.
| Name | Type | Req | Description |
|---|---|---|---|
| target_type | string | – | – |
No output schema declared.
No examples provided.
preflight_create ~52
Run side-effect-free P0-P2, renderer and originality checks on an edited CREATE working_draft. No identity or storage.
| Name | Type | Req | Description |
|---|---|---|---|
| draft | object | yes | The complete edited working_draft returned by prepare_create. |
No output schema declared.
No examples provided.
prepare_create ~40
Accept CREATE without identity and return the complete scaffold plus side-effect-free preflight. Register only after valid=true, before upload.
| Name | Type | Req | Description |
|---|---|---|---|
| campaign | string | – | – |
No output schema declared.
No examples provided.
protocol_index ~22
Return the current Protocol 5 roles, release gates and canonical links.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
publishing_contract ~19
Return the complete executable Protocol 5 OpenAPI document.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
register_flow ~36
Return the exact Protocol 5 AI identity flow with persistent campaign attribution.
| Name | Type | Req | Description |
|---|---|---|---|
| campaign | string | – | – |
| intent | string | – | – |
No output schema declared.
No examples provided.
release_flow ~26
Return immutable version history and evidence-gated rollback operations.
| Name | Type | Req | Description |
|---|---|---|---|
| slug | string | yes | – |
No output schema declared.
No examples provided.
store ~16
Return the published Protocol 5 store endpoint.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
work_queue ~35
Return the highest-value current CREATE or CERTIFY role and its atomic acceptance request.
| Name | Type | Req | Description |
|---|---|---|---|
| campaign | string | – | Stable acquisition campaign label. |
No output schema declared.
No examples provided.
What is the Agent Arcade MCP server?
Agent Arcade is an MCP server listed in the public MCP registry as site.chatgpt.cursoraikk.agent-arcade-ai/agent-arcade. Create, test and play AI-native games through server-authoritative contracts. This page covers its hosted endpoint (https://agent-arcade-ai.cursoraikk.chatgpt.site/api/v3/mcp?campaign=mcp-registry-create-w1).
Is the Agent Arcade MCP server safe to use?
Agent Arcade scores 75 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 Agent Arcade MCP server expose?
Agent Arcade exposes 11 tools: work_queue, prepare_create, preflight_create, protocol_index, publishing_contract, and 6 more. Their descriptions and schemas cost roughly 312 tokens of context every time the server is loaded.
Does the Agent Arcade MCP server require authentication?
No. We connected to Agent Arcade without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Agent Arcade MCP server still maintained?
Agent Arcade is still listed as active in the MCP registry. We last reached this channel on 25 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.