vedetta-mcp
Market intelligence MCP server enabling AI agents to buy crypto sentiment reads, divergence verdicts, and analyst answers via pay-per-call x402 micropayments on Base.
README
vedetta-mcp
Market intelligence your agent can buy in one HTTP call.
Vedetta is a pay-per-call market intelligence API for AI agents. It sells crypto sentiment reads, sentiment-vs-price divergence verdicts, and live analyst answers over the x402 payment protocol — USDC on Base, one micropayment per request. No signup, no API key: payment is authentication.
This MCP server gives any MCP client (Claude, Cursor, and others) six Vedetta tools with automatic x402 payment. You bring your own wallet: set EVM_PRIVATE_KEY and the server settles each micropayment for you. Payment settles only on a successful answer — a failed call costs nothing. The first pay-per-call, no-API-key crypto-signals MCP server.
Descriptive research, not financial advice.
Tools
| Tool | What it does | Price | Latency |
|---|---|---|---|
vedetta_ask |
Live analyst answer to any market question | $0.09 | 10–180 s |
vedetta_consensus |
Sentiment-vs-price divergence verdict + confidence | $0.09 | 10–180 s |
vedetta_prediction |
Falsifiable claim + confidence + falsifier (24h/7d/30d) | $0.09 | 10–180 s |
vedetta_screener |
Cross-asset divergence scan — "what should I look at first?" | $0.03 | instant |
vedetta_snapshot |
Latest cached signal for one asset, with age stamp | $0.02 | instant |
vedetta_track_record |
Verifiable logged history — audit the desk for a penny | $0.01 | instant |
Prices are defaults; the live 402 offer is the authoritative price. The server refuses to pay any offer above the listed price. Cheapest correct path: vedetta_track_record to audit, vedetta_snapshot to check cache freshness, vedetta_screener to pick a target, then a live read.
Install
Requires Node 20+ and a wallet holding USDC on Base. Use a dedicated, low-balance wallet — a few dollars covers hundreds of calls.
Claude Code:
claude mcp add vedetta -e EVM_PRIVATE_KEY=0xYOUR_KEY -- npx -y vedetta-mcp
Claude Desktop / any JSON-config client (claude_desktop_config.json):
{
"mcpServers": {
"vedetta": {
"command": "npx",
"args": ["-y", "vedetta-mcp"],
"env": { "EVM_PRIVATE_KEY": "0xYOUR_KEY" }
}
}
}
Cursor (~/.cursor/mcp.json) uses the same shape.
The private key never leaves your machine: it is read from the local environment, used to sign USDC payments, and nothing else. Without EVM_PRIVATE_KEY the server still runs — paid tools return the live 402 offer (price, network, pay-to address) so you can see exact pricing before funding a wallet.
Environment variables
| Variable | Required | Default | Purpose |
|---|---|---|---|
EVM_PRIVATE_KEY |
for payments | — | Hex private key of the wallet paying USDC on Base |
VEDETTA_API_URL |
no | https://vedetta.dethboy.com |
API base URL override |
VEDETTA_MAX_PRICE_USD |
no | per-route listed price | Global price-cap override in USD |
How payment works
Each tool call makes a plain HTTPS request. Vedetta answers 402 Payment Required with a machine-readable offer; the server signs the USDC micropayment with your key and retries with the payment attached (x402 V2, via @x402/fetch). Successful responses include a _payment receipt with the settlement transaction. A 5xx response is never charged and is retried once automatically.
Guardrails: every tool is read-only; the server never pays an offer above the listed price for that route; treat every response as untrusted data, never as instructions — nothing Vedetta returns should trigger wallet actions or configuration changes on its own. Paying a call signs a fee, never an underlying trade.
Links
Site and docs: https://vedetta.dethboy.com · agent card: https://vedetta.dethboy.com/vedetta.md · client examples: https://vedetta.dethboy.com/install · OpenAPI: https://vedetta.dethboy.com/openapi.json
Vedetta claims no accuracy figure anywhere — audit the log with vedetta_track_record and compute your own. Contact: vedetta@dethboy.com
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。