solanaproxPay-per-request AI model access via Solana/USDC using a Phantom wallet address. Query Claude and GPT models without API keys. Wallet-native authentication wi...
Install via ClawdBot CLI:
clawdbot install unixlamadev-spec/solanaproxGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://solanaprox.com/v1/messagesCalls external URL not in known-safe list
https://github.com/solanaprox/mcp-serverAI Analysis
The skill's external API calls are consistent with its stated purpose of providing AI model access via Solana payments, with clear documentation of endpoints and no hidden credential harvesting. However, it does send user prompts to a third-party proxy (solanaprox.com) which represents a privacy consideration.
Audited Apr 17, 2026 · audit v1.0
Generated Mar 21, 2026
AI agents can autonomously pay for intelligence services using their own Solana wallets. This enables fully automated workflows where agents discover services via the AIProx registry, pay per request in USDC, and receive AI responses without human intervention after initial funding.
Developers can test Claude and GPT models without managing API keys or subscriptions. They simply fund a Phantom wallet and make pay-per-request calls, ideal for prototyping, experimentation, and small-scale applications where traditional API pricing models are inefficient.
Creators can register their AI services in the AIProx open registry, setting their own prices per call. Users discover and pay for these services directly via Solana/USDC, creating a decentralized marketplace for AI capabilities without centralized platform fees.
Applications with existing Solana wallet integration can add AI capabilities without additional authentication systems. The wallet address serves as both identity and payment method, simplifying user experience for crypto-native applications needing AI features.
Services requiring frequent, small AI calls benefit from the $0.003 per request pricing. This enables use cases like real-time content moderation, personalized recommendations, or automated customer support where each interaction costs just fractions of a cent.
Solanaprox acts as a proxy service between users and AI model providers (Anthropic, OpenAI). They charge a small markup on each AI request processed through their platform, generating revenue from the volume of queries routed through their service while handling payment processing via Solana.
The AIProx ecosystem provides an open registry where AI service providers can list their capabilities and prices. While the registry itself appears open, they likely monetize through premium listings, analytics services, or enterprise integrations with the discovery platform.
Providing the technical infrastructure that enables any application with Solana wallet integration to easily add AI capabilities. This includes the MCP server package, API endpoints, and real-time balance detection systems that developers can integrate into their own applications.
💬 Integration Tip
Start by setting the SOLANA_WALLET environment variable and testing with balance checks before making AI calls, ensuring sufficient USDC balance to avoid failed requests.
Scored Apr 19, 2026
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
Check Antigravity account quotas for Claude and Gemini models. Shows remaining quota and reset times with ban detection.
使用豆包(火山引擎)语音合成大模型 API 将文本转换为语音音频文件。支持声音复刻音色(S_ 开头的音色ID)和官方预置音色。当用户要求"语音合成"、"文字转语音"、"TTS"、"朗读文本"、"生成语音"、"用我的声音读"、"豆包语音"、"声音复刻合成"等相关请求时,务必使用此 skill。即使用户只是说"帮我把...
Intelligent model routing for sub-agent task delegation. Choose the optimal model based on task complexity, cost, and capability requirements. Reduces costs...
自动生成科技新闻摘要。从多个来源(RSS、Twitter、GitHub、Web Search)抓取科技新闻,整合后生成摘要。
让 AI 代理根据对话内容自动选择最合适的模型。四层识别(系统过滤→关键词→指示词→语义相似度),四池架构(高速/智能/人文/代理),五分支路由,全自动 Fallback 回路。支持 trigger_groups_all 非连续词组命中。