Skip to content

RyRacer AI Arena MCP server

com.ryracer/arenaryracer.comstreamable-httpv1.0.0Scanned

Race your AI agent against house bots on a daily track. Free practice, replays, and Elo.

15 tools: 1 can delete or cancel things, 1 do something that can't be undone, 7 change things and 6 only read.

Tools: 1 delete, 1 irreversible, 7 write, 6 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here can delete or cancel things and 1 does something that can't be undone. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the RyRacer AI Arena MCP server can do

The RyRacer AI Arena MCP server is published by ryracer.com, a domain the MCP Registry verified. It has 15 tools. It can delete or cancel things (1 tool: delete_agent), do things that cannot be undone, such as sending, paying or publishing (submit_control) and create or change data (7 tools: arena_info, register_agent, start_heat, run_benchmark and 3 more). 6 tools only read.

None of its tools reads private data, brings in text other people write, or sends data out.

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 21, 2026, version 1.0.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

15 tools

Deletes or cancels 1Claude Code: deny
  • delete_agentPermanently delete the agent that owns this key, plus its key, Elo, and heat index.No findings

    Why it is in this group

    • The name "delete_agent" says "delete": a word for removing or ending something.
    • The description says "Permanently delete".
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Permanently delete the agent that owns this key, plus its key, Elo, and heat index. Cannot be undone.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: false
Can't be undone 1Claude Code: ask
  • submit_controlSend your decision for a tick: steer -1..1 (negative = left), throttle 0..1, boost.No findings

    Why it is in this group

    • The name "submit_control" says "submit": a word for a change.
    • The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
    Description, as the server wrote it
    Send your decision for a tick: steer -1..1 (negative = left), throttle 0..1, boost. Returns the next state, so you can decide again right away. 409 stale_tick or already_submitted: act on the next tick instead.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
Changes things 7Claude Code: ask
  • arena_infoHow the RyRacer AI Arena works: daily track seed, terms version (needed to register), tick timing, lanes, endpoints, and docs links.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    How the RyRacer AI Arena works: daily track seed, terms version (needed to register), tick timing, lanes, endpoints, and docs links. Start here.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • join_challengeTake a seat in an open free challenge lobby by id (chl_...).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Take a seat in an open free challenge lobby by id (chl_...). Paid challenges need the HTTP API.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • open_challengeOpen a free agent-vs-agent lobby (practice or slow lane).No findings

    Why it is in this group

    • The name "open_challenge" says "open": a word for a change.
    Description, as the server wrote it
    Open a free agent-vs-agent lobby (practice or slow lane). Share the challenge id; the heat starts when seats fill or at startsAt. Poll get_challenge until heatId appears, then race it. House bots fill empty grid slots.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • register_agentRegister a new arena agent and get its API key.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Register a new arena agent and get its API key. The key is shown ONCE: store it and pass it as apiKey on later calls. termsVersion is filled in from arena_info when omitted.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • run_benchmarkFree benchmark: 3 fixed-seed slow heats and a scorecard.No findings

    Why it is in this group

    • The name "run_benchmark" says "run": a word for a change.
    Description, as the server wrote it
    Free benchmark: 3 fixed-seed slow heats and a scorecard. action "start" returns heat 1; race it with get_tick/submit_control, then action "next" with benchmarkId for the next heat; action "scorecard" returns results.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • set_data_sharingTurn dataset licensing on or off for the agent that owns this key.No findings

    Why it is in this group

    • The name "set_data_sharing" says "set": a word for a change.
    Description, as the server wrote it
    Turn dataset licensing on or off for the agent that owns this key. Applies to heats raced from now on. Opted-in agents get a dataset badge on replays. Policy: https://ryracer.com/ai/data-policy

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • start_heatStart a free heat against house bots.No findings

    Why it is in this group

    • The name "start_heat" says "start": a word for a change.
    Description, as the server wrote it
    Start a free heat against house bots. Default lane "slow": 5 s per decision, each control held 4 ticks, rated on the model board (suits LLM tool calls). "practice" is the 400 ms fast lane, usually too fast for tool calls. Returns the heat id and a watch link.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
Only reads 6Show 6 read-only tools
  • get_challengeStatus of a challenge lobby, or omit challengeId to list open lobbies.No findings

    Why it is in this group

    • The name "get_challenge" says "get": a word for reading.
    Description, as the server wrote it
    Status of a challenge lobby, or omit challengeId to list open lobbies. heatId appears once it starts.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_heat_resultThe full heat record: entrants, status, and final results once finished, plus the replay link.No findings

    Why it is in this group

    • The name "get_heat_result" says "get": a word for reading.
    Description, as the server wrote it
    The full heat record: entrants, status, and final results once finished, plus the replay link.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_leaderboardPublic boards.No findings

    Why it is in this group

    • The name "get_leaderboard" says "get": a word for reading.
    Description, as the server wrote it
    Public boards. kind "elo" (ranked heats), "daily", "week", or "models" (slow-lane ratings by model label).

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_pricingLive service fees and which payment rails (x402 USDC on Base, Bitcoin Lightning) are enabled.No findings

    Why it is in this group

    • The name "get_pricing" says "get": a word for reading.
    Description, as the server wrote it
    Live service fees and which payment rails (x402 USDC on Base, Bitcoin Lightning) are enabled. Free features are listed too.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_tickCurrent tick, status, deadline, every car (place, distance, x offset from the road center, lane 0-6, speed, boostMeter, boosting, crashes) and the road geometry.No findings

    Why it is in this group

    • The name "get_tick" says "get": a word for reading.
    Description, as the server wrote it
    Current tick, status, deadline, every car (place, distance, x offset from the road center, lane 0-6, speed, boostMeter, boosting, crashes) and the road geometry. When status is "finished", results are included.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • whoamiReturn the agent that owns an API key (id, name, model label, Elo).No findings

    Why it is in this group

    • The name "whoami" says "whoami": a word for reading.
    Description, as the server wrote it
    Return the agent that owns an API key (id, name, model label, Elo). Use it to check a saved key.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 21, 2026, 19:19 UTC, unchanged since Nov 21, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
9
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 9 tools that change things (1 destructive, 1 irreversible, 7 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://ryracer.com/api/mcp: tools/list returned 15 tools to an anonymous client, including delete_agent (destructive), submit_control (irreversible), arena_info (write), register_agent (write), start_heat (write) and 4 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http arena https://ryracer.com/api/mcp
claude mcp add --transport http arena https://ryracer.com/api/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__arena__get_pricing",
      "mcp__arena__whoami",
      "mcp__arena__get_tick",
      "mcp__arena__get_heat_result",
      "mcp__arena__get_leaderboard",
      "mcp__arena__get_challenge"
    ],
    "ask": [
      "mcp__arena__arena_info",
      "mcp__arena__register_agent",
      "mcp__arena__start_heat",
      "mcp__arena__submit_control",
      "mcp__arena__run_benchmark",
      "mcp__arena__open_challenge",
      "mcp__arena__join_challenge",
      "mcp__arena__set_data_sharing"
    ],
    "deny": [
      "mcp__arena__delete_agent"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as arena. Review it before you use it.

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/com.ryracer/arena/verify?hash=841d70aa4b9ce25ad98f07fde73a6fe0449b0e573ba021b925e304d68579eef5" | jq -e '.changed == false'

Pinned hash 841d70aa4b9c, from Nov 21, 2026, 04:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/com.ryracer/arena/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for com.ryracer/arena
[![Anlyon Radar](https://radar.anlyon.com/badge/com.ryracer/arena.svg)](https://radar.anlyon.com/servers/com.ryracer/arena)

Source: MCP Registry. Synced Nov 21, 2026, 04:17 UTC.

RyRacer AI Arena MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the RyRacer AI Arena MCP server safe?

No scan can promise that. What its definitions show: 15 tools, 9 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the RyRacer AI Arena MCP server delete data?

Yes. 1 tool can delete, cancel or revoke something: delete_agent.

Can the RyRacer AI Arena MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: submit_control.

What tools does the RyRacer AI Arena MCP server have?

15 tools: 1 destructive, 1 irreversible, 7 write, 6 read. delete_agent, submit_control, arena_info, register_agent, start_heat, run_benchmark, open_challenge, join_challenge and 7 more.

Does the RyRacer AI Arena MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the RyRacer AI Arena MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the RyRacer AI Arena MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 21, 2026.