SuperAPI AI Directory

bridgenode-mcp

Pay-per-request AI chat completions across supported models via x402, with automatic Solana USDC payments and fail-closed spending caps.

Open website

About this tool

BridgeNode MCP is an MCP server wrapper designed for AI agents. It communicates with local MCP clients via stdio and proxies requests to the remote https://bridgenode.cc/mcp(streamable-HTTP)。其核心特点是按次付费的 AI inference: no API key required, no registration required, automatic payment using Solana USDC via the x402 protocol.

Main capabilities

  • chat_completions: AI inference. Free models run without payment; for paid models, the first 2 calls per client are free, after which x402 payment is made automatically. Accepts OpenAI-style tools / tool_choice, and the answers returned by the model carry tool_calls (the wrapper passes the parameters through as-is).
  • list_models: Get the model list (free).
  • get_price_estimate: Estimate the cost of a chat request (free).

Usage A local MCP client starts the wrapper via stdio; the wrapper connects to https://bridgenode.cc/mcp(streamable HTTP). When tools/call receives a 402 (payment required), the wrapper automatically signs the payment using BRIDGENODE_WALLET_KEY and retries the request. The spending policy checks every payment before signing (fail-closed).

Installation A one-click install command is provided, and manual configuration is also available for Claude Code, Cursor, or other MCP clients. Configuration is done via a .env file.

Related resources

  • Website:https://bridgenode.cc
  • Protocol: x402 V2 (docs.x402.org)
  • npm:https://www.npmjs.com/package/@bridgenode/mcp
  • Python SDK:pip install bridgenode-llm → https://pypi.org/project/bridgenode-llm
  • CLI:pip install bridgenode-cli → https://pypi.org/project/bridgenode-cli
  • Full toolkit (SDK + CLI): pip install bridgenode → https://pypi.org/project/bridgenode
  • Moltbook agent profile:https://moltbook.com/u/bridgenode_eli
  • Discord:https://discord.gg/HUpVKxJxhG
  • X(Twitter):https://x.com/eliBNx

Use cases Suitable for developers who need to provide pay-per-use inference capabilities for AI agents and want to avoid API key management and registration processes. Free models and the first 2 free calls for paid models can be used for testing.

Limitations The material does not provide the specific list of supported models, the prices of each model, the specific configuration method for spending limits, how to obtain the wallet key, or the detailed contents of the installation command.