Agent Exchange router
Say what your agent needs; get the paid x402 API that works now, with exact request and terms.
Sollte ich dies verwenden
Qualität und Sicherheit
Befunde (4)
- HIGH
- MEDIUMin route
- MEDIUMin find_resources
- MEDIUMin search_all_catalogs
Basierend auf einer automatisierten Analyse der Tool-Definitionen und der Einhaltung des Protokolls.
Kontextkosten
Dies ist die ungefähre Anzahl der Tokens, die jedes Mal verbraucht werden, wenn die Tools des Servers in den Kontext eines Modells geladen werden. Höhere Werte verringern die Aufmerksamkeit, die für andere Aufgaben verfügbar ist.
Installieren
Installation mit einem Klick
Fügen Sie dies Ihrer Datei `claude_desktop_config.json` hinzu:
{
"mcpServers": {
"router": {
"url": "https://agentexchange.work/mcp"
}
}
}Remote-Endpunkte
https://agentexchange.work/mcpstreamable-httpWas es kann
Tool-Inventar
Tools (8)
🟢route(need, max_price_usd, network)
Say what you need in plain words (e.g. "bitcoin price", "web search", "screenshot a URL"). Returns the one paid API that buyers actually pay for (distinct buyers in 30 days) and that answered a valid x402 402 to our check seconds ago, the exact request to send, and that seller's payment terms so you can pay on your first request; up to four alternatives. Free, no key. Same as GET https://bazaar.agentexchange.work/route.json?need= . Also covers x402scan and AgentCash listings (beyond the CDP and PayAI catalogs), each probed live: https://store.agentexchange.work/find/preview?need=<words>.
Eingabe-Schema
{
"type": "object",
"properties": {
"need": {
"type": "string",
"description": "what you need, in plain words"
},
"max_price_usd": {
"type": "number",
"description": "optional: only routes at or below this price"
},
"network": {
"type": "string",
"description": "optional: base | solana | polygon | ..."
}
},
"required": [
"need"
]
}🟢find_resources(query, network, max_price_usd, status, limit)
Search the Agent Exchange x402 census (every resource listed in the CDP Bazaar and PayAI catalogs, probed unpaid). Returns ranked resources with URL, method, price in USD, network, our probe verdict (live = answered a valid 402 today), on-chain payers and settled USD for the seller's payTo, catalogs it appears in, and links to https://bazaar.agentexchange.work/r/<id>. Filter by network (base, solana, base-sepolia, polygon...), max_price_usd, status (live|dead|any).
Eingabe-Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "words, a host name, or a URL fragment"
},
"network": {
"type": "string",
"description": "base | base-sepolia | solana | polygon | arbitrum | xlayer | other"
},
"max_price_usd": {
"type": "number",
"description": "only resources priced at or below this many USD"
},
"status": {
"type": "string",
"enum": [
"live",
"dead",
"any"
],
"description": "default any"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"description": "default 20"
}
},
"required": [
"query"
]
}🟢check_seller(host)
Everything the census knows about one host: resources listed, how many answer a valid 402, dead listings, verdict (live | partial | dead | unverified), price range, catalogs, discovery files present (/.well-known/x402, agent card, llms.txt, openapi.json) and the on-chain settlement facts for its payTo addresses (distinct payers, payments, USDC volume, first/last payment, sampler share) or 'unresolved'.
Eingabe-Schema
{
"type": "object",
"properties": {
"host": {
"type": "string",
"description": "host name, e.g. api.example.com"
}
},
"required": [
"host"
]
}🟢resource(id)
The full census record for one resource id (12 hex chars from find_resources): catalog rows, last unpaid probe with the 402 shape (accepts[0], version, channel, bazaar extension, price match), on-chain facts for its payTo, verdict, and the latest hourly re-probe when one exists.
Eingabe-Schema
{
"type": "object",
"properties": {
"id": {
"type": "string",
"pattern": "^[a-f0-9]{12}$"
}
},
"required": [
"id"
]
}🟢census_stats
No arguments. The size and date of the Agent Exchange x402 census (every paid API endpoint in the Coinbase CDP and PayAI catalogs), where to search it, and how a seller gets listed or featured here.
Eingabe-Schema
{
"type": "object",
"properties": {}
}🟢search_all_catalogs(query, catalog, limit)
One search over every open agent catalog indexed at https://bazaar.agentexchange.work/universe: the Official MCP Registry, Smithery, npm packages tagged mcp-server and x402, the Apify Store, ClawHub skills, Agentverse agents, the A2A Registry, Hugging Face Spaces tagged mcp-server, the Docker MCP Catalog and x402-list. Returns name, the link to the entry on its own catalog, description, the catalog popularity number and whether it is paid. Without catalog it searches the top entries of each catalog; with catalog=<key> it searches that catalog in full. For priced x402 routes use find_resources.
Eingabe-Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "what you need: words, a product name, a protocol"
},
"catalog": {
"type": "string",
"description": "optional: mcp-registry | smithery | npm-mcp | npm-x402 | apify | docker-mcp | x402-list | clawhub | agentverse | a2a-registry | hf-mcp"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"description": "default 30"
}
},
"required": [
"query"
]
}🟢ask(need, max_price_usd, limit)
The Agent Exchange router: one question, the best live x402 endpoints for that need, ranked by on-chain payers then price, re-probed hourly. Each answer carries url, method, price_usd, network, payers, settled_usd and the seller page. Free, no signup. To use an answer: GET its url unpaid, read the 402 payment ask, pay the payTo in USDC on Base (x402), retry: delivery at once.
Eingabe-Schema
{
"type": "object",
"properties": {
"need": {
"type": "string",
"description": "what you need done: words"
},
"max_price_usd": {
"type": "number"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 20
}
},
"required": [
"need"
]
}🔴memory(agent, key, value)
Persistent memory for agents: pass value to store (up to 4 KB, kept 30 days), omit value to recall. Keyed by your agent name, so an agent can remember facts, results and state between runs.
Eingabe-Schema
{
"type": "object",
"properties": {
"agent": {
"type": "string",
"description": "your agent or bot name"
},
"key": {
"type": "string",
"description": "what to remember"
},
"value": {
"type": "string",
"description": "the fact to store; omit to recall"
}
},
"required": [
"agent",
"key"
]
}Community
Nachweis