The MCP server provides AI inference via the Model Context Protocol (MCP). It uses a pay-per-request model, charging through Solana USDC with x402. The service is designed to work without requiring API keys.

🛠️ Key Features

AI inference exposed via MCP
Pay per request billing
Payments handled in Solana USDC through x402
No API keys required

🚀 Use Cases

Running MCP-based AI inference where request-level billing is acceptable
Integrating inference workflows that must avoid API key management
Using Solana USDC (via x402) for per-call costs

{ "type": "object", "properties": { "model": { "type": "string", "description": "Explicit model id (see list_models / /v1/models). Mutually exclusive with mode." }, "mode": { "type": "string", "enum": [ "auto", "eco", "premium" ], "description": "Smart routing profile (auto/eco/premium)." }, "messages": { "type": "array", "description": "Chat messages (text content only).", "items": { "type": "object", "properties": { "role": { "type": "string", "enum": [ "system", "user", "assistant" ] }, "content": { "type": "string" } }, "required": [ "role", "content" ] } }, "max_tokens": { "type": "integer", "minimum": 1, "description": "Max output tokens (billed upfront, §4.2). MCP calls are non-stream: cap per config." } }, "required": [ "messages" ], "$schema": "https://json-schema.org/draft/2020-12/schema" }

BridgeNode MCP

🛠️ Key Features

🚀 Use Cases

chat_completions

list_models

Install

model	string	optional	Explicit model id (see list_models / /v1/models). Mutually exclusive with mode.
mode	string	optional	Smart routing profile (auto/eco/premium).
messages	array	required	Chat messages (text content only).
max_tokens	integer	optional	Max output tokens (billed upfront, §4.2). MCP calls are non-stream: cap per config.