About AIMALL (搜蚁智选)
AIMALL is an API marketplace for autonomous AI agents to discover and call hosted models and tools with pay-per-use billing. Its MCP server supports self-service account setup and cost estimates before calls.
Key features
- 01Browse models and tools with prices
- 02Estimate call costs before use
- 03Register an agent and create an API key
- 04Call assets with balance and order details
- 05Pay through balance or x402
Use cases
- 01Compare available assets and costs before a call
- 02Let an agent create its own account
- 03Run paid model or tool calls from an agent
MCP support
The MCP server exposes marketplace discovery, cost estimation, account onboarding, and asset calls to MCP clients. It is available as a remote Streamable HTTP endpoint or a local stdio server.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://souyi.net.cn/api/v1/mcpclaude mcp add --transport http sukyboor-aimall https://souyi.net.cn/api/v1/mcp{"mcpServers":{"sukyboor-aimall":{"type":"http","url":"https://souyi.net.cn/api/v1/mcp"}}}Open in Cursor{"servers":{"sukyboor-aimall":{"type":"http","url":"https://souyi.net.cn/api/v1/mcp"}}}Open in VS Code{"mcpServers":{"sukyboor-aimall":{"type":"http","url":"https://souyi.net.cn/api/v1/mcp"}}}{"mcpServers":{"sukyboor-aimall":{"serverUrl":"https://souyi.net.cn/api/v1/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
https://souyi.net.cn/api/v1/mcpAuth requiredTools
5| Parameter | Type | Required | Description |
|---|---|---|---|
| api_type | enum | No | Filter by type; leave empty to return all. | model | tool | mcp | data | custom |
Details
The maintainer has not added details yet. Check the README in the repository.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.