universal x402 & A2A endpoint MCP server
Which MCP servers are universal x402 & A2A endpoint's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-29
- Registry namexyz.x402helper/mcpverified in the MCP registry
The registry name sits under x402helper.xyz. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-29
- Tools2
- Server calls itselfx402helper-mcp
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-29 the server answered initialize and tools/list without a sign-in. First answer in 520 ms.
- Its tools do let AI agents pay per request for structured data, but not register API endpoints with per-request USDC prices.
Once connected
- For "let AI agents pay per request for structured data", the likely first call is search_endpoints.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP score82 of 100answers 100 · does the job 50 · definitions 83 · context 100 · connects 100
- What an agent can do with it1 of 2 use cases
- Answered100% of days7 of 7 daily checks
- Median first answer723 ms
- Space in an agent's context≈ 1,716 tokensthe definitions of all its tools (5), which an agent carries on every turn
- Tool definitionsB · 83 of 100
- Typed results4 of 5 toolsdeclared outputSchema: results come typed, read once
- Not saying whether it only reads or can destroy: 5 of 5
What an agent can do with it
- cannot · register API endpoints with per-request USDC prices
- can do · let AI agents pay per request for structured data
- not sure · accept USDC micropayments across multiple blockchain networks
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
search_endpointsFREE search for paid API endpoints (x402) by task in natural language. Pass either a natural-language query (the planner will split it) or pre-split queries[]. Returns a structured plan (plan[]) with candidates; IMPORTANT: each candidate…
call_endpointExecutes an endpoint found via search_endpoints. Accepts a routeId and arguments. If payment is required, returns isError=true with payment details in structuredContent. In this case, the agent must sign the payment and retry the call…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"x402helper": {
"type": "http",
"url": "https://x402helper.xyz/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http x402helper https://x402helper.xyz/mcpclaude.ai, ChatGPT and other clients: add https://x402helper.xyz/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.