x402 Discovery & Trust MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| X402_MAX_USD | No | Maximum automatic payment in USD per call. 0 disables auto-pay. | 0.05 |
| X402_MAX_CALLS | No | Maximum paid calls per process. 0 = unlimited. | 1000 |
| X402_TIMEOUT_MS | No | HTTP request timeout in milliseconds. 0 uses the default of 20000. | 20000 |
| X402_PRIVATE_KEY | No | Optional Base wallet private key used for automatic USDC payments. Accepts 64 hexadecimal characters with or without the 0x prefix; surrounding whitespace is ignored. An invalid key logs a warning and disables auto-pay. | |
| X402_MAX_TOTAL_USD | No | Cumulative auto-pay spending limit in USD per process. 0 = unlimited. | 1.00 |
| X402_TRUST_API_BASE | No | Base URL of the x402 Trust API. | https://x402-trust.com |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| x402_ecosystem_statsA | Snapshot of the whole x402 ecosystem: endpoint counts, reachability, and real USDC settlement volume over 30 days. Use it to gauge market health. |
| x402_trust_leaderboardA | Top-100 ranking of the most trustworthy x402 hosts, scored by their whole measured surface. Page with offset, then use x402_search to list a host's endpoints. |
| x402_verified_providersB | List of hosts that proved domain control and confirmed a contact email. Verification is informational only, it never changes the score. |
| x402_searchA | Substring search over host, URL and service name across the catalog. For meaning-based search use x402_semantic_search instead. |
| x402_trust_previewA | Sample pack: three complete trust reports (best, median, worst) exactly as x402_trust_score returns them. Takes no arguments. |
| x402_trust_scoreB | The full trust verdict for one x402 endpoint: score 0-100, grade, recommendation (proceed, caution, avoid, ...), price, and flags. Unknown endpoints get live-probed on the spot. |
| x402_endpoint_historyA | Raw probe and event history for one endpoint over 1-90 days: price and payTo changes, failures, latencies, plus a summary. Excluded probes never count as downtime. |
| x402_find_alternativesA | Finds semantically similar endpoints that out-score a given one. Empty result means nothing beats it. |
| x402_semantic_searchA | Meaning-based search across the catalog: describe the capability you need in plain words. Discovery only, no verdicts. |
| x402_trust_bulkA | Score up to 500 endpoints in one call; the cheapest fitting tier is picked automatically. Unknown URLs come back found:false, the batch is charged either way. |
| x402_watch_createB | 30-day monitor for one endpoint with alerts on payTo or price changes, delisting, spec regressions and downtime, via polling or webhooks. Returns a one-time secret, keep it. |
| x402_watch_eventsA | Poll a watch's event log with watch_id and secret, paging by the returned cursors. Nothing between polls is lost. |
| x402_watch_editB | Change a watch's webhook URLs, sensitivity or subscribed events. New URLs are tested first; failures leave the old config untouched. |
| x402_watch_cancelA | Stop a watch now; its log stays readable until expiry. Idempotent. |
| x402_watch_renewA | Add another 30 days to an active watch. Same secret. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 15 tools
Each tool targets a distinct action on a distinct resource: watch lifecycle (create/edit/cancel/renew/events), search versus semantic_search, and the trust family (score, bulk, preview, leaderboard). Descriptions explicitly disambiguate overlapping cases, e.g. x402_search tells users to use x402_semantic_search for meaning-based queries, and preview is clarified as a sample pack of score output.
All tools follow a uniform x402_-prefixed snake_case convention with a clear domain verb/noun pattern (watch_create, trust_score, semantic_search, find_alternatives). The noun-only names (endpoint_history, ecosystem_stats) still fit the same predictable scheme.
Fifteen tools for a discovery-and-trust domain is well-scoped and each earns its place across the search, trust-scoring, and watch-management surfaces. No redundancy that would bloat the set.
The surface covers discovery, trust scoring (single/bulk/preview/leaderboard), history, ecosystem stats, and full watch lifecycle including events. The main gap is a 'list watches' operation — watch_events requires a watch_id, so an agent that loses the id has no way to enumerate its watches.