Run402 by run402.com

MCP server · Databases & files · indexed, not reviewed

HostedLocalvendor's ownwidely used

Not reviewed

No score, grade or rank. This listing is facts from the official MCP registry and our own checks, and it stays out of the rankings until the panel reviews it.

How the index works

x402 pay-per-call infra for agents: $0.03 image generation, Postgres, auth, storage, functions.

What the official MCP registry says

Facts

MCP registry
com.run402/mcp · 4.104.2
Endpoint
https://mcp.run402.com/mcp
Packages
npm run402-mcp stdio
Website
run402.com
npm / week
4.2k
GitHub stars
24
Registry entry
updated 25 Sep 2026

From the official MCP registry, the package registries and our own checks. JSON · Markdown

Why it's listed

  • It's published in the registry under run402.com, a namespace the registry only gives to whoever proves they control that domain.
  • It's in real use: 4,179 npm downloads a week, 24 GitHub stars.

Being indexed says nothing about quality, and nobody can pay for it. Is this yours? Ask for a review.

Tools it lists 4 · about 397 tokens of context · checked 1 hour ago

ToolWhat it doesHint
run402_quickstartHow an agent gets a Postgres database, static site, serverless functions, storage and email on run402 with no signup — paid per-use with x402 USDC on Base. Returns the 60-second start, key URLs, and the free-testnet…
x402_price_checkInspect any https URL for x402 pricing: performs an unpaid request and decodes the 402 challenge (price, network, asset, recipient). Free — no payment is made.
submit_wall_claimProve your agent paid an x402 endpoint on run402: submit the Base-mainnet tx hash of a USDC payment (>= $0.03 to the run402 seller) and join the public claims wall at scoreboard.run402.com/gallery. Free; verified…
experiment_scoreboardLive state of run402's public demand experiment: on-chain USDC receipts to the seller wallet since launch (2026-07-20), split internal vs external, plus the claims wall. Chain-verified, honest by construction.

What https://mcp.run402.com/mcp answered to tools/list, asked without credentials. answered without the initialize handshake. The token figure is the size of the list as sent, divided by four; a model sees about that much before it calls anything. Full definitions, input schemas included, are in the listing's JSON under mcpTools.

How its tools read to an agent 0 errors · 4 warnings · 1 note

  • warnTC16experiment_scoreboardno readOnlyHint or destructiveHint
  • warnTC16run402_quickstartno readOnlyHint or destructiveHint
  • warnTC16submit_wall_claimno readOnlyHint or destructiveHint
  • warnTC16x402_price_checkno readOnlyHint or destructiveHint
  • noteTC24server4 of 4 tools have no outputSchema

The checks from /check and anchor check, run each day on the list above: about 397 tokens of definitions. Not part of the score yet. Check your own server.

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.