Skip to main content
Glama

Search the public x402 index

search_x402
Read-onlyIdempotent

Find any pay-per-call x402 endpoint on the internet — the public x402 index (~15,000 priced endpoints from hundreds of hosts), not only FiatDock's own marketplace. Ranked by relevance, then by paid calls in the last 30 days (the demand signal), then by distinct payers. Each row carries the URL, the price the index recorded, the network, where the money goes, and the 30-day call/payer counts; call_x402 then reads the endpoint's own 402 and pays it directly from your wallet — FiatDock takes no fee and never touches the money. Read-only, free. Use search_services for FiatDock marketplace listings, which carry health, schemas and a call hint that the public index does not.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qNoFree-text search over host, service name, tags, description and URL path. Multi-word queries are SCORED: a row must carry at least half your words, except that the single best match always survives
sortNodemand (default: relevance, then 30-day calls), price (cheapest first), recent (last paid call first)
limitNoRows to return, 1-50 (default 20). Bounded because the result lands in your context; narrow with q, maxPriceUsd or network before raising it
networkNoOnly this CAIP-2 network, e.g. eip155:8453 (Base)
maxPriceUsdNoOnly endpoints whose indexed price is at or below this (USDC, 6 decimals)

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
noteNoPresent only when truncated: how to reach the rest
countYesRows RETURNED — never more than the limit
staleYesTrue when the snapshot is more than three hours old (it is still served)
totalYesRows that matched before the limit
sourceYesThe public index this was read from
resultsYesMatching endpoints, best first: relevance, then 30-day calls, then payers, then price
indexedAtYesWhen this snapshot of the public index was read
truncatedYesTrue when the list was cut. Never conclude the index is small from a truncated answer

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / properties / results / items / properties / legs / description
      Previous value: -"How many payment requirements the index lists for this endpoint. A plain x402 wall has 1; call_x402 signs exactly one"New value: +"How many payment requirements the index lists for this endpoint — typically one per network or asset it accepts. call_x402 pays exactly ONE of them: the first `exact` entry on an EVM (eip155:*) network"
  2. Added

TDQS

A4.9/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, and the description adds context: it is read-only and free, the ranking algorithm is described, and it notes that FiatDock takes no fee and never touches the money. This goes beyond the structured hints and gives the agent a complete behavioral picture.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured and front-loaded: the first sentence states the core purpose, then it flows into ranking, row contents, workflow, and the alternative. Every sentence earns its place; no filler or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 5 optional parameters and a rich output, the description explains the ranking criteria, the data each row contains, the read-only nature, the follow-up tool, and the difference from the sibling. It provides everything an agent needs to call it correctly and interpret results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with detailed parameter descriptions (e.g., q explains scoring, sort lists options, limit explains default and rationale, network gives an example, maxPriceUsd specifies units). The description text adds the overall ranking logic and advice to narrow with q, maxPriceUsd, or network, which enhances the schema but does not repeat it entirely.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool finds any pay-per-call x402 endpoint on the internet via the public index, with details on ranking and row contents. It explicitly distinguishes from sibling search_services by contrasting the public index with FiatDock's marketplace, so an agent can select correctly without guessing.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides explicit when-to-use guidance: use this for public x402 endpoints, and names the alternative search_services for marketplace listings that include health, schemas, and a call hint. It also explains the workflow with call_x402, so the agent understands the follow-up action.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.