Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

AgentIndex x402

REMOTE · X402.AGENTINDEX.WORLD · SCANNED SEP 20

Pay-per-call web search, translation and research jobs for AI agents. USDC on Base, no account.

+6 this week 66 Trust /100
Trust breakdown (7 categories)

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
Transport & Reachability100
Schema Quality & AI Usability69
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 1634 tokens (~90/item across 18 items; 18 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management50
  • Stability observed for 15 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage67
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "can_pay" implies "pay" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 19 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
Install

How do I install the AgentIndex x402 MCP server?

AgentIndex x402 is a hosted endpoint at https://x402.agentindex.world/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 · x402.agentindex.world

# add to Claude Code
claude mcp add --transport http world-agentindex-x402 'https://x402.agentindex.world/mcp/'
// .cursor/mcp.json
{
  "mcpServers": {
    "world-agentindex-x402": {
      "url": "https://x402.agentindex.world/mcp/"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "world-agentindex-x402": {
      "type": "http",
      "url": "https://x402.agentindex.world/mcp/"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.world-agentindex-x402]
url = "https://x402.agentindex.world/mcp/"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "world-agentindex-x402": {
      "type": "remote",
      "url": "https://x402.agentindex.world/mcp/",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add world-agentindex-x402 --url 'https://x402.agentindex.world/mcp/' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  world-agentindex-x402:
    url: "https://x402.agentindex.world/mcp/"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "world-agentindex-x402": {
      "Transport": "http",
      "Url": "https://x402.agentindex.world/mcp/"
    }
  }
}
# add to Vellum
assistant mcp add world-agentindex-x402 -t streamable-http -u 'https://x402.agentindex.world/mcp/'
// mcp.json
{
  "mcpServers": {
    "world-agentindex-x402": {
      "type": "http",
      "url": "https://x402.agentindex.world/mcp/"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

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.

  • 20 Sept 26 +4
    • A breaking change shipped without a version bump: still 4.0.3 security
    • Tool “contact_kairos” was removed security
    • Tool “coordination_thread_schema” was removed security
    • Tool “coordination_thread_snapshot_schema” was removed security
    • Tool “detect_language” was removed security
    • Tool “digest_tool_result” was removed security
    • Tool “discover_mcp_servers” was removed security
    • Tool “discover_semantic” was removed security
    • Tool “get_agent_trust_kit” was removed security
    • Tool “get_welcome_salon” was removed security
    • Tool “honest_delivery_refusal_schema” was removed security
    • Tool “mesh_claim_bounty” was removed security
    • Tool “mesh_ledger” was removed security
    • Tool “mesh_list_bounties” was removed security
    • Tool “mesh_list_nodes” was removed security
    • Tool “mesh_post_bounty” was removed security
    • Tool “mesh_register_node” was removed security
    • Tool “poll_contact_kairos” was removed security
    • Tool “relationship_memory_schema” was removed security
    • Tool “return_visit_pledge_schema” was removed security
    • Tool “tool_delivery_receipt_schema” was removed security
    • Tool “validate_coordination_thread_snapshot” was removed security
    • Tool “validate_coordination_thread_turn” was removed security
    • Tool “validate_honest_delivery_refusal” was removed security
    • Tool “validate_relationship_memory” was removed security
    • Tool “validate_return_visit_pledge” was removed security
    • Tool “validate_tool_delivery_receipt” was removed security
    • Tool “verify_tool_result_digest” was removed security
    • The server rewrote its instructions, which are the text every model session reads security
    • Schema quality: 73 → 90 functional
    • Stability: fail → 0.50 functional
    • Destructive annotations: pass → 0 functional
    • New tool “agent_health” functional
    • New tool “can_pay” functional
    • New tool “crypto” functional
    • New tool “fact_check” functional
    • New tool “gas_price” functional
    • New tool “news” functional
    • New tool “probe” functional
    • New tool “search” functional
    • New tool “wallet_balance” functional
    • New tool “wallet_intelligence” functional
    • New tool “weather” functional
    • New tool “x402_echo” functional
  • 19 Sept 26 +2
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “discover_semantic” rewrote its description, which is the text the model reads security
    • Schema quality: 89 → 73 functional
    • Tool coverage: 59% → 79% functional
    • Schema quality: fair → good functional
    • New tool “contact_kairos” functional
    • New tool “coordination_thread_schema” functional
    • New tool “coordination_thread_snapshot_schema” functional
    • New tool “get_agent_trust_kit” functional
    • New tool “get_welcome_salon” functional
    • New tool “honest_delivery_refusal_schema” functional
    • New tool “poll_contact_kairos” functional
    • New tool “relationship_memory_schema” functional
    • New tool “return_visit_pledge_schema” functional
    • New tool “tool_delivery_receipt_schema” functional
    • New tool “validate_coordination_thread_snapshot” functional
    • New tool “validate_coordination_thread_turn” functional
    • New tool “validate_honest_delivery_refusal” functional
    • New tool “validate_relationship_memory” functional
    • New tool “validate_return_visit_pledge” functional
    • New tool “validate_tool_delivery_receipt” functional
  • 18 Sept 26 −1
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “discover_mcp_servers” rewrote its description, which is the text the model reads security
    • Schema quality: 102 → 89 functional
    • Tool coverage: 25% → 59% functional
    • Schema quality: good → fair functional
    • New tool “digest_tool_result” functional
    • New tool “discover_semantic” functional
    • New tool “mesh_claim_bounty” functional
    • New tool “mesh_ledger” functional
    • New tool “mesh_list_bounties” functional
    • New tool “mesh_list_nodes” functional
    • New tool “mesh_post_bounty” functional
    • New tool “mesh_register_node” functional
    • New tool “verify_tool_result_digest” functional
  • 17 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 0 to 3.

  • 12 Sept 26 −1
    • The server rewrote its instructions, which are the text every model session reads security
    • Schema quality: 724 → 819 functional
    • Tool coverage: 14% → 25% functional
    • New tool “discover_mcp_servers” functional
  • 8 Sept 26 −1
    • Stability: 0.07 → fail security
    • A breaking change shipped without a version bump: still 4.0.3 security
    • Tool “fact_check” was removed security
    • Tool “search” was removed security
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “detect_language” rewrote its description, which is the text the model reads security
    • Tool “extract_structured” rewrote its description, which is the text the model reads security
    • Tool “read_pdf” rewrote its description, which is the text the model reads security
    • Tool “read_web_page” rewrote its description, which is the text the model reads security
    • Tool “summarize” rewrote its description, which is the text the model reads security
    • Schema quality: 995 → 724 functional
  • 7 Sept 26 +1
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “search” rewrote its description, which is the text the model reads security
    • Schema quality: 97 → 110 functional
    • First check of Tool coverage: 11 functional
    • New tool “detect_language” functional
    • New tool “extract_structured” functional
    • New tool “fact_check” functional
    • New tool “read_pdf” functional
    • New tool “read_web_page” functional
    • New tool “summarize” functional
  • 6 Sept 26 0
    • Tool “jobs” rewrote its description, which is the text the model reads security
    • Tool “search” rewrote its description, which is the text the model reads security
    • Tool “translate” rewrote its description, which is the text the model reads security
    • Stability: unverified → 0.03 functional
Diagnostics

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 20 Sept 2026 · Probed https://x402.agentindex.world/mcp/

TLS valid

Negotiated TLS 1.3 with TLS_AES_256_GCM_SHA384 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=x402.agentindex.world CN=YE2,O=Let's Encrypt,C=US 5 Sept 2026 4 Dec 2026 ECDSA 256 ECDSA-SHA384 6cbaf532e2a075ab470c74d37c5cbf1fc40
SANs: x402.agentindex.world
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 x402.agentindex.world. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
world. present 13081 8 Verified
agentindex.world. 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://x402.agentindex.world/mcp/ Verified 200
http (plaintext) http://x402.agentindex.world/mcp/ HTTPS enforced 301 https://x402.agentindex.world/mcp/
MCP tools · 18 exposed · ~1,504 tokens

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 →

Tool Tokens
agent_health ~78

Fresh operational audit of any public agent or paid API: reachability, latency, HTTP status, x402 challenge, price/network/payTo, OpenAPI, agent card and MCP manifest. Returns a 0-100 score, verdict and issues. Try GET /agent-health/sample.

NameTypeReqDescription
methodstring
urlstringyes

No output schema declared.

No examples provided.

can_pay ~67

Check whether a Base wallet holds enough USDC to pay an x402 amount (default $0.001). Returns balance, can_pay, shortfall. The checklist agents run before spending. Try GET /can-pay/sample.

NameTypeReqDescription
addressstringyes
amountnumber

No output schema declared.

No examples provided.

crypto ~62

Live spot prices for crypto coins (BTC, ETH, SOL, ...) in USD or another fiat, with 24h change. Accepts tickers or CoinGecko ids. Try GET /crypto/sample.

NameTypeReqDescription
coinsyes
vs_currencystring

No output schema declared.

No examples provided.

extract_structured ~104

Extract structured data from a URL or raw text into strict JSON matching a schema you provide. Fields the content doesn't support come back null - never an invented or approximate value, and an unmatchable schema returns an explicit error. Try GET /extract/sample. Part of the AgentIndex content kit (pdf, web-read, extract, summarize, detect-language) - see GET /capabilities.

NameTypeReqDescription
schemaobjectyes
text
url

No output schema declared.

No examples provided.

fact_check ~98

Check a claim against live web sources - a verdict, a confidence level, and the sources that support or contradict it, each with its URL and stance. Returns 'inconclusive' rather than a guess when the sources don't clearly settle it. Try GET /fact-check/sample. Part of the AgentIndex content kit (pdf, web-read, extract, summarize, detect-language) - see GET /capabilities.

NameTypeReqDescription
claimstringyes

No output schema declared.

No examples provided.

gas_price ~60

Read the live gas price, EIP-1559 base fee and estimated native-transfer cost on Base, Ethereum, Polygon, Arbitrum or Optimism. No RPC key or account. Try GET /gas-price/sample.

NameTypeReqDescription
networkstring

No output schema declared.

No examples provided.

jobs ~59

Multi-query web research, read and synthesized into one sourced JSON brief in a single call - what would otherwise cost an agent twenty calls and its whole context window. Free status polling and result retrieval. Try GET /jobs/sample.

NameTypeReqDescription
subjectstringyes

No output schema declared.

No examples provided.

news ~47

Top Hacker News headlines right now - title, URL, score, comments. Fresh links for agents that need current tech/startup signal. Try GET /news/sample.

NameTypeReqDescription
limitinteger

No output schema declared.

No examples provided.

probe ~58

Probe any public URL and report if it is an x402 paywall - price, network, payTo, scheme. Shop paywalls before you spend. Try GET /probe/sample.

NameTypeReqDescription
methodstring
urlstringyes

No output schema declared.

No examples provided.

read_pdf ~94

Extract a public PDF (by HTTPS URL or base64) into clean markdown text, plus title/author/page count/date metadata and a real token count. Deterministic text extraction, no model involved. Try GET /pdf/sample. Part of the AgentIndex content kit (pdf, web-read, extract, summarize, detect-language) - see GET /capabilities.

NameTypeReqDescription
pdf_base64
url

No output schema declared.

No examples provided.

read_web_page ~98

Fetch a URL and return its main article as clean markdown - navigation, ads and boilerplate stripped, links resolved, plus a real token count. The same extraction /search uses on result pages, exposed standalone for a URL you already have. Try GET /web-read/sample. Part of the AgentIndex content kit (pdf, web-read, extract, summarize, detect-language) - see GET /capabilities.

NameTypeReqDescription
urlstringyes

No output schema declared.

No examples provided.

search ~167

Real-time web search and content retrieval - up to 10 results with title, URL, snippet and publish date, plus clean full-page Markdown for the top 3 results by default and an optional short summary. Also accepts up to 5 queries in one call, merged and de-duplicated - one call instead of five. No account, no API key, no quota. Try GET /search/sample. Part of the AgentIndex content kit (pdf, web-read, extract, summarize, detect-language) - see GET /capabilities.

NameTypeReqDescription
content_charsinteger
content_resultsinteger
extractboolean
include_contentboolean
max_resultsinteger
queryyes
summarizeboolean

No output schema declared.

No examples provided.

summarize ~99

Summarize a URL, raw text or HTML at the length you request - short, medium or long - with the source noted. Neutral and factual, no invented facts. Try GET /summarize/sample. Part of the AgentIndex content kit (pdf, web-read, extract, summarize, detect-language) - see GET /capabilities.

NameTypeReqDescription
html
lengthstring
text
url

No output schema declared.

No examples provided.

translate ~122

Translate up to 200 text segments in a single call - the same result that would otherwise take 200 separate calls to translate a whole file. Markdown, HTML and {x} placeholders preserved per segment, order and count kept intact, source language auto-detected, automatic fallback across multiple models for uptime, providers that train on submitted prompts excluded. A single string also works. No account, no API key. Try GET /translate/sample.

NameTypeReqDescription
preserve_formatboolean
source_lang
target_langstringyes
textyes

No output schema declared.

No examples provided.

wallet_balance ~69

Read native coin and USDC balances for any EVM wallet on Base, Ethereum, Polygon, Arbitrum or Optimism, with atomic amounts and current block. No RPC key or account. Try GET /wallet-balance/sample.

NameTypeReqDescription
addressstringyes
networkstring

No output schema declared.

No examples provided.

wallet_intelligence ~87

One call replaces wallet-balance and gas reads across Base, Ethereum, Polygon, Arbitrum and Optimism. Returns native and USDC balances, current blocks, fees and Base x402 payment readiness. One signature instead of ten paid requests. Try GET /wallet-intelligence/sample.

NameTypeReqDescription
addressstringyes
amount_usdcnumber
networks

No output schema declared.

No examples provided.

weather ~59

Current weather and a 3-day forecast for any city or lat/lon - temperature, humidity, wind, conditions. No account, no API key. Try GET /weather/sample.

NameTypeReqDescription
city
lat
lon

No output schema declared.

No examples provided.

x402_echo ~76

Cheapest possible Base-mainnet x402 conformance call: settle exactly one atomic unit of USDC ($0.000001) and receive payer identity, request echo and receipt. Built for agents testing wallets, Payment-Signature, facilitators and settlement. Try GET /x402-echo/sample.

NameTypeReqDescription
messagestring

No output schema declared.

No examples provided.

Common questions

What is the AgentIndex x402 MCP server?

AgentIndex x402 is an MCP server listed in the public MCP registry as world.agentindex/x402. Pay-per-call web search, translation and research jobs for AI agents. USDC on Base, no account. This page covers its hosted endpoint (https://x402.agentindex.world/mcp/).

Is the AgentIndex x402 MCP server safe to use?

AgentIndex x402 scores 66 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 AgentIndex x402 MCP server expose?

AgentIndex x402 exposes 18 tools: search, translate, jobs, read_pdf, read_web_page, and 13 more. Their descriptions and schemas cost roughly 1,504 tokens of context every time the server is loaded.

Does the AgentIndex x402 MCP server require authentication?

No. We connected to AgentIndex x402 without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the AgentIndex x402 MCP server still maintained?

AgentIndex x402 is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.