BlackSwan MCP Server
Enables AI agents to access real-time crypto risk intelligence with two tools: Flare for precursor detection and Core for overall risk environment assessment.
README
BlackSwan MCP Server
Real-time crypto risk intelligence via the Model Context Protocol. Two AI agents monitor what's happening 24/7 — before news breaks, as it breaks, and why it happened. Enables agents to have real-time risk intelligence and awareness, not yesterday's news.
Tools
| Tool | What it answers |
|---|---|
| Flare | "Is something happening right now?" — Precursor detection from a 15-minute signal window |
| Core | "What's the overall risk environment?" — State synthesis from a 60-minute signal window |
Connect
MCP
Point any MCP client at:
https://mcp.blackswan.wtf/mcp
No API key required.
REST API
curl -s https://mcp.blackswan.wtf/api/flare
curl -s https://mcp.blackswan.wtf/api/core
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"blackswan": {
"type": "http",
"url": "https://mcp.blackswan.wtf/mcp"
}
}
}
Then ask Claude: "What does Flare say about current crypto risk?"
Response Format
Flare
| Field | Description |
|---|---|
agent |
Always "flare" |
data_age |
Human-readable age (e.g. "12 minutes ago") |
status |
"clear" or "alert" |
severity |
"none", "low", "medium", "high", or "critical" |
checked_at |
ISO 8601 timestamp |
assessment |
Natural language risk assessment |
signals |
Array of detected signals with type, source, and detail |
Core
| Field | Description |
|---|---|
agent |
Always "core" |
data_age |
Human-readable age (e.g. "1 hour ago") |
timestamp |
ISO 8601 timestamp |
environment |
"stable", "elevated", "stressed", or "crisis" |
assessment |
Natural language risk assessment |
key_factors |
Array of main risk factors |
sources_used |
Data sources used in the assessment |
data_freshness |
How fresh the underlying data is |
Interpreting Results
Flare Severity
| Level | Meaning |
|---|---|
none |
No precursors detected, markets quiet |
low |
Minor signals, worth noting but not actionable |
medium |
Notable signals, warrants attention |
high |
Strong precursors, elevated risk of sudden moves |
critical |
Extreme signals, immediate risk of major event |
Core Environment
| Level | Meaning |
|---|---|
stable |
Normal conditions, low systemic risk |
elevated |
Above-normal risk, some stress indicators |
stressed |
Significant stress across multiple indicators |
crisis |
Severe market stress, active dislocation or contagion |
Error Responses
| HTTP Status | Meaning |
|---|---|
200 |
Success |
502 |
Agent output failed validation |
503 |
No recent agent runs — system may be starting up |
500 |
Unexpected server error |
Non-200 responses return {"error": "..."} with a human-readable message.
License
MIT
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。