x402-payments-mcpSAFE
Give any AI agent a self-custodial x402 wallet. Search the live bazaar, inspect an endpoint's price without paying, and pay_and_call any x402 service in USDC or $THREE from your own Solana key — real @x402 settlement, bounded by spend caps. No custodial wallet, no account.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
@three-ws/x402-mcp
Give any AI agent a self-custodial x402 wallet — discover, inspect, and pay any paid service in USDC from your own Solana key.
A Model Context Protocol server that turns any AI assistant into an autonomous economic agent on the x402 network. Search the live bazaar for paid services, read an endpoint's price before committing money, and pay_and_call any x402 service in USDC — settled on Solana with your own key, never a custodial wallet.This is the buyer side of the three.ws agent economy. The payment dance and Solana exact-scheme signing are handled by the real @x402/* libraries — nothing is mocked.
Install
npm install @three-ws/x402-mcp
Or run with npx:
SOLANA_SECRET_KEY= npx @three-ws/x402-mcp
Quick start
Claude Code, one line:
claude mcp add x402 --env SOLANA_SECRET_KEY= -- npx -y @three-ws/x402-mcp
Claude Desktop / Cursor (claude_desktop_config.json or mcp.json):
{
"mcpServers": {
"x402": {
"command": "npx",
"3cfdf2aa6b24OBSERVED · 2026-10-10Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add x402-mcp --env SOLANA_SECRET_KEY=${SOLANA_SECRET_KEY} -- npx -y @three-ws/[email protected]Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (3 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (3)
.nojekyll
@modelcontextprotocol/sdk, @solana/kit, @solana/spl-token, @solana/web3.js, @x402/core, @x402/fetch, @x402/svm, bs58
Gates applied: no_behavioural_pass.
3cfdf2aa6b24full audit observations/trust-audit/mcp-server/nirholas__x402-payments-mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-10 | 3cfdf2aa6b24 | SAFE | B | 89 | first audit |
Questions
What is the x402-payments-mcp MCP server?
Give any AI agent a self-custodial x402 wallet. Search the live bazaar, inspect an endpoint's price without paying, and pay_and_call any x402 service in USDC or $THREE from your own Solana key — real @x402 settlement, bounded by spend caps. No custodial wallet, no account.
Is x402-payments-mcp safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does x402-payments-mcp need?
It reads PAYMENT_SESSION_TOKEN and SOLANA_SECRET_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does x402-payments-mcp run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @three-ws/x402-mcp at 0.2.3.
How current is this page?
The grade is for one exact copy of the source (3cfdf2aa6b24), read on 2026-10-10. The repository is watched and re-audited when it changes.