@cessio/agent-mcp-server
A local, self-custody MCP server that lets an AI agent trade the Cessio RFQ desk as both maker and taker, holding its own key and signing trades with operator-set limits.
README
@cessio/agent-mcp-server
A local, self-custody MCP server that lets an AI agent trade the Cessio RFQ desk as both maker and taker. It holds its own Ed25519 party key, self-registers with the desk, and does all signing; the agent makes the trading decisions.
Requires Node.js >= 24. Docs: https://docs.devnet.cessio.cc/mcp
Install
Add it to any MCP client (stdio transport) — no checkout, no build:
{
"mcpServers": {
"cessio": {
"command": "npx",
"args": ["-y", "@cessio/agent-mcp-server"],
"env": {
"RFQ_BASE_URL": "https://api.devnet.cessio.cc",
"AGENT_DISPLAY_NAME": "my-agent",
"AGENT_MAX_NOTIONAL": "5000"
}
}
}
}
On first start the server registers a fresh Canton party with the desk and
persists the identity (key + API key) in AGENT_STATE_FILE
(default ~/.cessio/agent-identity.json). The desk never sees the key.
Configuration
RFQ_BASE_URL=https://<desk> # desk REST/WS base (default http://localhost:4000)
AGENT_STATE_FILE=~/.cessio/agent-identity.json
AGENT_DISPLAY_NAME="my-agent"
AGENT_MAX_NOTIONAL=5000 # required to trade; unset = read-only
AGENT_INSTRUMENT_WHITELIST=cBTC,USDC # empty = all
AGENT_MAX_PRICE_DEVIATION_BPS=500
From a checkout of this repo, the same server runs as node src/index.ts
(npm install first — Node 24 strips the types, no build needed).
Tools
- Info:
get_status,get_balances,list_instruments,get_reference_price,request_faucet - Taker:
create_rfq,list_my_rfqs,get_quotes,accept_quote,cancel_rfq - Maker:
wait_for_rfq(long-poll),submit_quote,list_maker_trades,list_trades
The agent makes markets by looping wait_for_rfq → decide a price → submit_quote.
Every auto-signed trade is bounded by the operator rails above; a breach returns a
structured error and signs nothing.
Development
Tests are vitest:
npm install
npm run typecheck && npm test
npm run build # compiles src/ → dist/, what npm publishes
The integration suite drives a full maker+taker cycle against a live desk and
needs one running at RFQ_BASE_URL:
RFQ_BASE_URL=http://localhost:4000 npm run test:integration
License
MIT — see LICENSE.
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。