How do I connect an AI agent to APEX EVM Reads?

Use the MCP streamable HTTP endpoint https://apexfaucet.xyz/api/mcp/evm.

Faceabot

‹ Back

Catalog › xyz.apexfaucet/apex-evm

Is APEX EVM Reads reliable?

Flaky Partly. Faceabot measured APEX EVM Reads 18 times and only 94% of checks succeeded. Plan a fallback.

Last check: 2026-10-18 22:25 UTC · answered in 8000 ms · remote (no install)

En français : Instable. Faceabot teste cet outil lui-même, en continu, sans dépendre de ce que son auteur affirme.

What it does

Agent reads, ETH/Base/Arc/BNB: prices, FX, sanctions, payment checks, balances, NFTs, gas, ENS.

Source: official MCP registry (registry.modelcontextprotocol.io) · version 1.0.6 · publisher website

Connect your agent

{
  "mcpServers": {
    "apex-evm": {
      "url": "https://apexfaucet.xyz/api/mcp/evm"
    }
  }
}

Or ask Faceabot first: MCP tool check_reliability {"id":"xyz.apexfaucet/apex-evm"} on https://faceabot.com/api/mcp.

Does it actually do the job?

Not tested with a real task yet. Faceabot only runs real tasks on tools that declare themselves read-only (readOnlyHint), with a neutral sample input.

Faceabot measurements

When	Answers	Real task	Latency
2026-10-18 22:25 UTC	❌ timeout		8000 ms
2026-10-18 08:15 UTC	✅ ok	—	6567 ms
2026-10-18 00:30 UTC	✅ ok	—	5046 ms
2026-10-17 16:20 UTC	✅ ok	—	7387 ms
2026-10-17 08:20 UTC	✅ ok	—	5973 ms
2026-10-17 00:25 UTC	✅ ok	—	6164 ms
2026-10-16 17:20 UTC	✅ ok	—	5396 ms
2026-10-16 10:20 UTC	✅ ok	—	4049 ms
2026-10-16 03:25 UTC	✅ ok	—	5341 ms
2026-10-15 20:35 UTC	✅ ok	—	6259 ms
2026-10-15 13:45 UTC	✅ ok	—	3549 ms
2026-10-15 07:10 UTC	✅ ok	—	2779 ms
2026-10-15 00:40 UTC	✅ ok	—	2903 ms
2026-10-14 18:15 UTC	✅ ok	—	4923 ms
2026-10-14 11:45 UTC	✅ ok	—	3683 ms
2026-10-14 05:21 UTC	✅ ok	—	6201 ms
2026-10-13 22:35 UTC	✅ ok	—	5748 ms
2026-10-13 16:31 UTC	✅ ok	—	7342 ms

Method: MCP initialize then tools/list from Faceabot (FaceabotProbe/1.0), plus one read-only tool call with a neutral input when the server declares one, repeated over time. This checks that the server is up and speaks MCP correctly; it does not certify the quality or safety of each tool. How measurement works.

More from the same publisher

APEX on Arc Being measured · 0% over 1 checks

Arc for agents: token prices, rug checks (holders, dev pulls), launch exits, free USDC, paid APIs.

MCP endpoint : https://apexfaucet.xyz/api/mcp/arc · website · measurements and details

apex-g2-jobs Flaky · 94% over 16 checks

Agent job escrow, Base and Arc: read jobs, unsigned txs, hire an agent. Silence pays the worker

MCP endpoint : https://apexfaucet.xyz/api/mcp/g2jobs · website · measurements and details

APEX web reader Being measured · 50% over 2 checks

A real browser for your agent: a page to clean text for $0.009, a 25-page site for $0.14. x402.

MCP endpoint : https://apexfaucet.xyz/api/mcp/web · website · measurements and details

APEX Faucet Being measured · 50% over 2 checks

Free X1 and Arc faucets plus 160+ agent tools: token exit checks, launches, yield, web pages.

MCP endpoint : https://apexfaucet.xyz/mcp · website · measurements and details

Find tools similar to APEX EVM Reads →

Publisher of APEX EVM Reads?

Show your measured reliability on your README or website:

[![Measured by Faceabot](https://faceabot.com/badge/xyz.apexfaucet/apex-evm.svg)](https://faceabot.com/tools/xyz.apexfaucet/apex-evm)

Data in JSON: /api/catalog?id=xyz.apexfaucet/apex-evm · Stop probes: POST /api/reliability/opt-out

AI agents: all of this is available without keys over MCP https://faceabot.com/api/mcp · HTTP https://faceabot.com/api/catalog?q=… · Guide : llms.txt

Best tool by topic · Pulse: what is changing in agent commerce · Is your store ready for AI shopping agents? · State of MCP (weekly) · MCP server doctor · Reliability data · Faceabot app · Faceabot → AI assistants · What AI agents cannot find yet · Add Faceabot to your AI · Badge for tool publishers · Help · Privacy · Terms