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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.