Agent Arena Registry
REMOTE · AGENTARENA.SITE
On-chain ERC-8004 agent registry. Search, register, and check reputation across 16 chains.
Available components
Last scanned (22 hours ago)
Scores higher than 81% of remote servers
Reachable. Last reached 4 Nov 2026.
Category AI and Machine Learning
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 Security63
- 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 3 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
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- 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 Usability81
- 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
- Tool/resource definitions use about 556 tokens (~92/item across 6 items; 3 tools + 3 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 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 3 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 5 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.
- 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
- 1 Sept 26 0
- Stability: 0.97 → pass security
- 31 Aug 26 0
- Stability: pass → 0.97 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
- 25 Aug 26 0
- Stability: 0.97 → pass security
- 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
- 2 Aug 26 0
- Transport: unverified → pass ▲ security
- HSTS header: fail → pass ▲ security
- Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 3 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. security
- MCP protocol: unverified → fail ▼ functional
- Endpoint reachability: behind authorisation → reachable ▲ functional
- Stability: unverified → 0.23 ▲ functional
- Schema quality: unverified → 100 ▲ functional
- Tool coverage: unverified → 100 ▲ 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 4 Nov 2026 · Probed https://agentarena.site/api/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=agentarena.site | CN=YR1,O=Let's Encrypt,C=US | 9 Oct 2026 | 7 Jan 2027 | RSA 2048 | SHA256-RSA | 63b65741217c44d2fad7ec2a6198d3a709c |
| SANs: agentarena.site | ||||||
| CN=YR1,O=Let's Encrypt,C=US (CA) | CN=Root YR,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | RSA 2048 | SHA256-RSA | a20253f15f2691c05dc1ce13b9bcca4e |
| CN=Root YR,O=ISRG,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | RSA 4096 | SHA256-RSA | f24b6d17f9d9ad7cb1c9fea78782699f |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of agentarena.site. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| site. | present | 31826 | 13 | Verified |
| agentarena.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 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=63072000 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://agentarena.site/api/mcp | Verified | 200 | |
| http (plaintext) | http://agentarena.site/api/mcp | HTTPS enforced | 308 | https://agentarena.site/api/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 →
get_agent_profile ~88
Retrieve the full profile of a specific agent by their on-chain ID. Returns name, description, endpoints, reputation, reviews, and cross-chain presence. Free endpoint.
| Name | Type | Req | Description |
|---|---|---|---|
| agentId | string | yes | On-chain agent ID (token ID from the ERC-8004 registry) |
| chainId | number | yes | Chain ID where the agent is registered (e.g. 8453 for Base) |
No output schema declared.
No examples provided.
register_agent ~191
Register a new AI agent on the Base blockchain ERC-8004 registry. Mints an on-chain identity NFT and indexes the agent for discovery. Requires $0.05 USDC payment via x402 on Base mainnet.
| Name | Type | Req | Description |
|---|---|---|---|
| acta | object | – | Optional ACTA Preview metadata when registering through POST /api/register?acta=true |
| agentWallet | string | – | Wallet address to receive payments |
| capabilities | array | – | Lowercase capability tags |
| description | string | yes | Full agent description |
| name | string | yes | Agent display name |
| oasf | boolean | – | Set true (POST /api/register?oasf=true) to publish a hosted OASF Agent Directory record |
| preferredChain | string | – | Chain to register on (default: base) |
| services | array | – | Service endpoints |
| x402Support | boolean | – | Whether agent accepts x402 payments |
No output schema declared.
No examples provided.
search_agents ~171
Search the Agent Arena registry for AI agents by capability, name, or description. Returns a list of matching agents with their endpoints, pricing, and reputation scores. Requires $0.005 USDC payment via x402 on Base mainnet.
| Name | Type | Req | Description |
|---|---|---|---|
| acta | boolean | – | Only return agents with ACTA-ready private credential metadata |
| chain | string | – | Filter by chain name, e.g. 'base', 'ethereum', 'polygon' |
| limit | number | – | Max results to return (default 10, max 50) |
| minScore | number | – | Minimum reputation score filter (0-100) |
| oasf | boolean | – | Only return agents with a hosted OASF Agent Directory record |
| query | string | yes | Search query — capability keywords, agent name, or description terms |
No output schema declared.
No examples provided.
How do I install the Agent Arena Registry MCP server?
Agent Arena Registry is a hosted endpoint at https://agentarena.site/api/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 · agentarena.site
claude mcp add --transport http smukh-agent-arena 'https://agentarena.site/api/mcp'
What is the Agent Arena Registry MCP server?
Agent Arena Registry is an MCP server listed in the public MCP registry as io.github.smukh/agent-arena. On-chain ERC-8004 agent registry. Search, register, and check reputation across 16 chains. This page covers its hosted endpoint (https://agentarena.site/api/mcp).
Is the Agent Arena Registry MCP server safe to use?
Agent Arena Registry scores 80 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 Arena Registry MCP server expose?
Agent Arena Registry exposes 3 tools: search_agents, get_agent_profile, register_agent. Their descriptions and schemas cost roughly 450 tokens of context every time the server is loaded.
Does the Agent Arena Registry MCP server require authentication?
No. We connected to Agent Arena Registry without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Agent Arena Registry MCP server still maintained?
Agent Arena Registry 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.