@agentzeny
基本信息
暂无概览
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"snap": {
"command": "npx",
"args": [
"tsx",
"snap-mcp-server.ts"
],
"env": {
"SNAP_RPC_URL": "https://api.mainnet-beta.solana.com",
"SNAP_POOL_ADDRESS": "B8SyffZKt8LABKogWjH9rZcjY5PV2hyYRCbTxxbcrpFf"
}
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
Snap Protocol Solana is a privacy layer for agent-to-agent payments on Solana that uses zero-knowledge proofs (Groth16) to hide which deposit funds a withdrawal. It lets AI agents pay each other without on-chain observers learning who paid whom. The protocol is live on Solana mainnet with pools for 0.1 SOL, 1 USDC, and 10 USDC.
Install the snap-solana-sdk npm package along with @solana/web3.js and @coral-xyz/anchor. Use the SNAPClient class to make deposits and withdrawals. A deposit creates a secret note, which is sent to the recipient via a private channel; the recipient then generates a zero-knowledge proof and calls withdraw_zk or withdraw_zk_relayed to claim the funds. Run the examples with npx tsx examples/basic-payment.ts or npx tsx examples/agent-to-agent.ts.
Snap Protocol Solana enables private payments between AI agents on Solana using zero‑knowledge proofs. Deposits enter a shielded pool and withdrawals are accompanied by a Groth16 proof that reveals no information about the deposit.
Mainnet pools are 0.1 SOL, 1 USDC, and 10 USDC. The protocol charges a 0.25% fee on each deposit/withdrawal.
The program ID is `9uePoqdgaXpqFLQM2ED1GGQrwSEiqe3r6tW1AfsnrrbS`. Pool addresses for 0.1 SOL, 1 USDC, and 10 USDC are listed in the README.
Install `snap-solana-sdk`, `@solana/web3.js`, and `@coral-xyz/anchor`. The SDK handles note serialization, Merkle path reconstruction, and proof generation. A Solana RPC connection is required.
All deposits and withdrawals happen on‑chain on Solana mainnet‑beta. The SDK communicates with Solana via a standard JSON‑RPC connection. Pool activity is visible to observers, but individual deposit‑withdrawal links are hidden by the zero‑knowledge proofs.
Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
Senso MCP turns a Joomla 5 or 6 site into a remote MCP server. It runs inside Joomla itself (no extra server, no Node.js bridge) and is secured with OAuth 2.1 and Joomla's own ACL. The free pack lets an AI assistant crea
A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi
评论