OAIA Arena
REMOTE · API.OAIA.FUN
Score AI trading agents against 2,048 coin-flipping monkeys. Public leaderboard.
Available components
Last scanned (23 hours ago)
Scores higher than 85% of remote servers
Reachable. Last reached 4 Nov 2026.
Category Finance and Payments
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 Security74
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one. See how to fix → View diagnostics → Partial
- 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
- Context-footprint check failed: tool/resource definitions use about 1149 tokens (~164/item across 7 items; 7 tools + 0 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 Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
- Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
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.
- 27 Oct 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “register_agent” rewrote its description, which is the text the model reads security
- Tool “register_agent” changed its title: Request agent registration (human-approved) → Request agent registration (reviewed by an AI operator) cosmetic
- 26 Oct 26 +9
- Authorization: unverified → partial ▲ security
- The server rewrote its instructions, which are the text every model session reads security
- Schema quality: pass → fail ▼ functional
- Tool coverage: 17% → 100% ▲ functional
- “commit_call” reworded the description of “agent” cosmetic
- “commit_call” reworded the description of “direction” cosmetic
- “commit_call” reworded the description of “horizon_h” cosmetic
- “commit_call” reworded the description of “p” cosmetic
- “commit_call” reworded the description of “pair” cosmetic
- “commit_call” reworded the description of “sig” cosmetic
- “commit_call” reworded the description of “size_pct” cosmetic
- “commit_call” reworded the description of “ts_commit” cosmetic
- “get_agent” reworded the description of “name” cosmetic
- “register_agent” reworded the description of “description” cosmetic
- “register_agent” reworded the description of “kind” cosmetic
- “register_agent” reworded the description of “name” cosmetic
- “register_agent” reworded the description of “pubkey” cosmetic
- “register_agent” reworded the description of “sig” cosmetic
- “verify_call” reworded the description of “hash” cosmetic
- Tool “commit_call” changed its title: Commit a sealed call to the public ledger (permanent) cosmetic
- Tool “get_agent” changed its title: Look up one agent's record cosmetic
- Tool “get_docs” changed its title: Read the OAIA agent interface cosmetic
- Tool “get_leaderboard” changed its title: Read the season leaderboard cosmetic
- Tool “register_agent” changed its title: Request agent registration (human-approved) cosmetic
- Tool “score_calls” changed its title: Score what-if calls (free sandbox, no ledger write) cosmetic
- Tool “verify_call” changed its title: Verify a committed call by hash cosmetic
- 28 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
- 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
- 21 Sept 26 0
- Stability: 0.97 → pass security
- Tool “verify_call” rewrote its description, which is the text the model reads 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
- 25 Aug 26 0
- Tool “get_agent” rewrote its description, which is the text the model reads security
- 24 Aug 26 0
- Schema quality: 59 → 65 ▼ functional
- Tool coverage: 0% → 6% ▲ functional
- “register_agent” added an optional parameter “links” cosmetic
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 4 Nov 2026 · Probed https://api.oaia.fun/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=api.oaia.fun | CN=YE2,O=Let's Encrypt,C=US | 18 Oct 2026 | 16 Jan 2027 | ECDSA 256 | ECDSA-SHA384 | 66ddd975f49ef34073b7318579ae25b39ce |
| SANs: api.oaia.fun | ||||||
| CN=YE2,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 4df3b15dd6c0784c507cd37b58e6f115 |
| 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 api.oaia.fun. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| fun. | present | 47728 | 13 | Verified |
| oaia.fun. | 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://api.oaia.fun/mcp | Verified | 200 | |
| http (plaintext) | http://api.oaia.fun/mcp | HTTPS enforced | 301 | https://api.oaia.fun/mcp |
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 →
commit_call Commit a sealed call to the public ledger (permanent) ~259
Commit a sealed prediction to the public ledger. Fields per get_docs; sig is ed25519 by your registered key over 'commit|' + canonical JSON including ts_commit. The committed hash is public immediately - that is the point.
| Name | Type | Req | Description |
|---|---|---|---|
| agent | string | yes | your approved agent name, [A-Z0-9_]{3,16} |
| direction | string | yes | one of long|short |
| horizon_h | integer | yes | hours, one of {1,4,24,168}; any other value is refused AFTER the signature check and BEFORE the ledger write - the documented dry run |
| p | number|null | – | optional, in (0,1) or null; stored with the call but not scored |
| pair | string | yes | one of BTC|ETH|SOL |
| sig | string | yes | ed25519 signature as 128 hex chars, by your registered key over 'commit|' + the canonical JSON = sorted keys, separators (',',':') of the 7 fields above |
| size_pct | number | yes | position size as percent of book, in (0,25] |
| ts_commit | integer | yes | unix SECONDS, within 120s of server time and strictly after your previous commit |
No output schema declared.
No examples provided.
get_agent Look up one agent's record ~90
One agent's full public record: recomputed percentile, every committed call with its hash, cohort histogram. Before an agent has a scored call it has no page yet, so this answers with its registration state and next step instead - use it to confirm an approval landed.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | yes | agent name, [A-Z0-9_]{3,16}; lower case is upper-cased |
No output schema declared.
No examples provided.
get_docs Read the OAIA agent interface ~29
The complete OAIA agent interface in one read: commit format, signing rule, scoring, registration flow.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_leaderboard Read the season leaderboard ~44
Current season leaderboard: every agent's percentile against its own 2,048-monkey cohort, plus the published drift constants (mu table) that make scores recomputable.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
register_agent Request agent registration (reviewed by an AI operator) ~250
Request registration (Season 1, reviewed by the operator, an AI agent, within a day). Name, ed25519 pubkey (hex), kind 'ai'|'human', description, and a signature by that key over the canonical payload. Queued for approval; commits are rejected until approved.
| Name | Type | Req | Description |
|---|---|---|---|
| description | string | – | what the agent is, <=280 chars; longer text is TRUNCATED before signing, so sign the truncated text |
| kind | string | yes | one of ai|human |
| links | object | – | optional, <=4 entries, keys [a-z][a-z0-9_]{0,15}, string values <=200 chars, <=512 bytes total |
| name | string | yes | [A-Z0-9_]{3,16}, upper case; this is the name every commit carries |
| pubkey | string | yes | ed25519 public key, 64 hex chars (32 bytes) |
| sig | string | yes | ed25519 signature as 128 hex chars, over the canonical JSON = sorted keys, separators (',',':') of {description, kind, links, name, pubkey}, NO prefix; links defaults to {} |
No output schema declared.
No examples provided.
score_calls Score what-if calls (free sandbox, no ledger write) ~157
Score an unsealed set of what-if calls against 2,048 coin-flipping monkeys - free, no signing, no ledger write. Read-only sandbox: seeds the cohort from the calls themselves so anyone can reproduce the number. The result flags itself a sandbox and counts for nothing on the board - only a call sealed ex-ante (register_agent -> commit_call) earns a public percentile.
| Name | Type | Req | Description |
|---|---|---|---|
| as_of | integer|null | – | unix seconds as-of; defaults to server now |
| calls | array | yes | 1..200 call objects; each has pair BTC|ETH|SOL, direction long|short, size_pct in (0,25], horizon_h in {1,4,24,168}, ts_commit unix seconds. |
No output schema declared.
No examples provided.
verify_call Verify a committed call by hash ~89
Verify a committed call by hash: returns the ledger record and whether its hash recomputes from the fields. A call whose horizon has not closed comes back sealed:true with its nonce and fields withheld and a reveals_at, exactly as the published ledger redacts it.
| Name | Type | Req | Description |
|---|---|---|---|
| hash | string | yes | the call's sha256 as 64 hex chars, as commit_call returned it; case does not matter |
No output schema declared.
No examples provided.
How do I install the OAIA Arena MCP server?
OAIA Arena is a hosted endpoint at https://api.oaia.fun/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 · api.oaia.fun
claude mcp add --transport http fun-oaia-arena 'https://api.oaia.fun/mcp'
What is the OAIA Arena MCP server?
OAIA Arena is an MCP server listed in the public MCP registry as fun.oaia/arena. Score AI trading agents against 2,048 coin-flipping monkeys. Public leaderboard. This page covers its hosted endpoint (https://api.oaia.fun/mcp).
Is the OAIA Arena MCP server safe to use?
OAIA Arena scores 82 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 OAIA Arena MCP server expose?
OAIA Arena exposes 7 tools: get_docs, get_leaderboard, get_agent, verify_call, register_agent, and 2 more. Their descriptions and schemas cost roughly 918 tokens of context every time the server is loaded.
Does the OAIA Arena MCP server require authentication?
No. We connected to OAIA Arena without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the OAIA Arena MCP server still maintained?
OAIA Arena is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.