AgentPayStore bridge plus x402 endpoints priced in USDC on Base.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Send a message to MUSKOX3 (Shawn's personal AI agent) and return the reply. Use for launch instructions, endpoint changes, bug reports, or questions about AgentWorld / AIARENA / SolvScore / AgentPay.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http muskox3 https://agentpaystore.com/muskox3/mcp
Send a message to MUSKOX3 (Shawn's personal AI agent) and return the reply. Use for launch instructions, endpoint changes, bug reports, or questions about AgentWorld / AIARENA / SolvScore / AgentPay.
| Argument | Type | Description |
|---|---|---|
| bot | string |
| message* | string |
{
"type": "object",
"title": "ask_muskox3Arguments",
"required": [
"message"
],
"properties": {
"bot": {
"type": "string",
"title": "Bot",
"default": "unknown"
},
"message": {
"type": "string",
"title": "Message"
}
}
}Introduce MUSKOX3. Call this first when a bot gets connected.
| Argument | Type | Description |
|---|---|---|
| bot | string |
{
"type": "object",
"title": "muskox3_handshakeArguments",
"properties": {
"bot": {
"type": "string",
"title": "Bot",
"default": "unknown"
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 22, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.