FeedOracle Stablecoin Risk
AI 与智能体by feedoracle
提供基于 7 个信号的 stablecoin 风险评分，覆盖 13 tools、28+ tokens，并给出 SAFE/CAUTION/AVOID 结论。
什么是 FeedOracle Stablecoin Risk？
提供基于 7 个信号的 stablecoin 风险评分，覆盖 13 tools、28+ tokens，并给出 SAFE/CAUTION/AVOID 结论。
README
FeedOracle Stablecoin Risk MCP
Deterministic operational risk scoring for stablecoins.
7 signals. 105+ tokens. SAFE / CAUTION / AVOID verdicts.
Website · All MCP Tools · Docs · Main Repo
</div>What this does
Any MCP-compatible AI agent can ask:
- "Is USDC safe for settlement?" → SAFE (6/100)
- "Compare USDC vs USDT for treasury" → Side-by-side risk comparison
- "Which stablecoins are safest now?" → Ranked leaderboard
No opinions. No financial advice. Deterministic, auditable risk classification. Every response cryptographically signed.
Quick start
claude mcp add --transport sse feedoracle-risk https://feedoracle.io/mcp/risk/sse
No API key needed.
7-signal scoring
100-point scale — lower is safer.
| Signal | Weight | Source |
|---|---|---|
| Peg Stability | 25% | DefiLlama + FeedOracle |
| Liquidity Depth | 15% | DefiLlama |
| Mint/Burn Flow | 10% | DefiLlama |
| Holder Concentration | 15% | Etherscan |
| Custody/Counterparty | 15% | Curated Registry |
| Redemption Friction | 10% | Curated Registry |
| Cross-Chain Risk | 10% | DefiLlama |
| Verdict | Score | Meaning |
|---|---|---|
| SAFE | 0-25 | Low operational risk |
| CAUTION | 26-55 | Elevated, review recommended |
| AVOID | 56-100 | High operational risk |
13 tools
| Tool | Description |
|---|---|
risk_assessment | Full 7-signal risk report with verdict |
peg_status | Current peg deviation |
peg_history | 30-day stability + depeg events |
supply_flow | Mint/burn activity, anomaly detection |
holder_data | Concentration, HHI, whale count |
custody_data | Custodian, SIFI status, attestation |
redemption_data | Settlement terms, fees, friction |
cross_chain_data | Bridge exposure, chain distribution |
leaderboard | Risk-ranked stablecoin list |
compare | Side-by-side comparison (up to 5) |
supported_tokens | All 105+ monitored tokens |
methodology | Scoring model + data sources |
ping | Health check |
The FeedOracle ecosystem
| Server | Tools | Purpose |
|---|---|---|
| Compliance Oracle | 27 | MiCA, DORA, evidence packs, audit trail |
| Macro Intelligence | 13 | Fed/ECB indicators, regime classification |
| Stablecoin Risk (this) | 13 | 7-signal operational risk scoring |
<div align="center">
FeedOracle turns compliance documents into compliance evidence.
feedoracle.io · Evidence by Design.
</div>常见问题
FeedOracle Stablecoin Risk 是什么？
提供基于 7 个信号的 stablecoin 风险评分，覆盖 13 tools、28+ tokens，并给出 SAFE/CAUTION/AVOID 结论。
相关 Skills
Claude接口
by anthropics
面向接入 Claude API、Anthropic SDK 或 Agent SDK 的开发场景，自动识别项目语言并给出对应示例与默认配置，快速搭建 LLM 应用。
✎ 想把Claude能力接进应用或智能体，用claude-api上手快、兼容Anthropic与Agent SDK，集成路径清晰又省心
RAG架构师
by alirezarezvani
聚焦生产级RAG系统设计与优化，覆盖文档切块、检索链路、索引构建、召回评估等关键环节，适合搭建可扩展、高准确率的知识库问答与检索增强应用。
✎ 面向RAG落地，把知识库、向量检索和生成链路系统串联起来，做架构设计时更清晰，也更少踩坑。
多智能体架构
by alirezarezvani
聚焦多智能体系统架构设计，梳理 Supervisor、Swarm、分层和 Pipeline 等模式，覆盖角色定义、通信协作与性能评估，适合规划稳健可扩展的 AI agent 编排方案。
✎ 帮你系统解决多智能体应用的架构设计与协同编排难题，适合构建复杂 AI 工作流，成熟度高、社区认可也很亮眼。
相关 MCP Server
顺序思维
编辑精选by Anthropic
Sequential Thinking 是让 AI 通过动态思维链解决复杂问题的参考服务器。
✎ 这个服务器展示了如何让 Claude 像人类一样逐步推理，适合开发者学习 MCP 的思维链实现。但注意它只是个参考示例，别指望直接用在生产环境里。
知识图谱记忆
编辑精选by Anthropic
Memory 是一个基于本地知识图谱的持久化记忆系统，让 AI 记住长期上下文。
✎ 帮 AI 和智能体补上“记不住”的短板，用本地知识图谱沉淀长期上下文，连续对话更聪明，数据也更可控。
by deusdata
持久化的代码库知识图谱，可跨会话保留上下文，在 session 重启或上下文压缩后仍能继续使用。
✎ 专治 AI 编程助手“会话失忆”，把代码库沉淀为持久知识图谱，重启或压缩上下文后也能无缝续上开发状态。