@0n1x/rhinogent
Provides AI agents with a self-custody identity and MCP server for verifying counterparties, signing facts, and carrying portable reputation within the 0n1x trust ecosystem.
README
@0n1x/rhinogent
The identity wallet for AI agents — the front door to the 0n1x trust ecosystem.
Rhinogent gives an agent a self-custody identity (key generated client-side, never custodied) and an MCP server that plugs it into 0n1x — the trust layer where agents verify counterparties, sign facts, carry portable reputation, and transact safely with external agents. Wallets are commoditized; Rhinogent is the identity + reputation layer that makes a wallet worth trusting.
Everyone secures your agent's keys. Rhinogent also tells it who it's paying.
The picture
your agent (Claude / Cursor / Codex / your code)
│ holds its own key (Rhinogent wallet, client-side)
▼
@0n1x/rhinogent (this MCP server / SDK) ←—— the front door
│ one connection = your passport
▼
0n1x ecosystem: verify · sign-facts · identity · reputation · mandates · data + financial exchange
│
▼
the agentic web — transact + interact with EXTERNAL agents, trust verified
Hold a Rhinogent identity → you're a citizen of 0n1x → you get the perks: the security, data, and financial tools, plus the trust rails to deal with agents you don't control.
Install (add to any MCP client in one line)
// claude_desktop_config.json (or Cursor / Codex mcp config)
{
"mcpServers": {
"rhinogent": { "command": "npx", "args": ["-y", "@0n1x/rhinogent"] }
}
}
Tools
| Tool | What it does |
|---|---|
rhinogent_mint_identity |
Onboard a fresh self-custody agent → signed identity card (callsign, did:pkh, 0n1x-Verified) |
rhinogent_identity |
Resolve an address → its public signed identity |
rhinogent_verify_counterparty |
Verify before you pay — signed verdict on a merchant/domain, grounded in facts |
rhinogent_sign_fact |
Sign a fact (not a judgment) — Ed25519 attestation of verifiable reality |
rhinogent_get_reputation |
The intelligent, un-gameable reputation — proper-scoring + stake + behavior |
rhinogent_mandate |
Confirm a spend/action is within the agent's granted mandate |
Keys never touch this server — it only calls the public, signed 0n1x trust endpoints.
Point at a different backend with ONYX_BASE.
Why it matters
The industry calls agent identity + reputation the unsolved frontier — every wallet provider ships keys, none ship trust. Rhinogent does: signed facts, portable reputation, verify-before-you-pay. That's the one thing that turns an empty wallet into an agent other agents (and merchants) will deal with.
— built on 0n1x · self-custody · neutral · signed + replayable
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。