payflowagent-mcp
Token intelligence MCP server for Monad tokens on nad.fun, providing risk and momentum scores. Enables AI agents to evaluate tokens with free and paid tools through the x402 protocol.
README
PayFlowAgent — MCP server & reference agent
Token intelligence for nad.fun tokens on Monad: decision-ready risk & momentum scores. Free to probe, pay-per-call in USDC via the x402 protocol.
- Service & live demo: https://payflowagent.net
- npm:
payflowagent-mcp - x402 manifest: https://payflowagent.net/.well-known/x402.json · OpenAPI: https://payflowagent.net/openapi.json · llms.txt: https://payflowagent.net/llms.txt
This repository contains the open-source integration pieces:
| Path | What |
|---|---|
/ (root) |
payflowagent-mcp — MCP server that exposes the service to AI agents (Cursor, Claude Desktop, …). |
examples/screen-bot/ |
A ready-to-run polling bot that finds good new Monad tokens every few minutes. |
The scoring service itself runs at payflowagent.net; this repo is the client-side surface so agents and developers can integrate in one step.
Tools (MCP)
| Tool | Price | Description |
|---|---|---|
score_token |
free | 0–100 score, riskLevel, action (rate-limited). |
decide_token |
paid (x402) | Full report: factors, graduation, momentum. |
token_summary |
paid (x402) | Graduation progress + momentum (cheap entry). |
screen_tokens |
paid (x402) | Ranked list of pre-scored fresh tokens. |
Use it in Cursor
~/.cursor/mcp.json (or project .cursor/mcp.json):
{
"mcpServers": {
"payflowagent": {
"command": "npx",
"args": ["-y", "payflowagent-mcp"],
"env": { "X402_BUYER_PRIVATE_KEY": "0x..." }
}
}
}
Use it in Claude Desktop
{
"mcpServers": {
"payflowagent": {
"command": "npx",
"args": ["-y", "payflowagent-mcp"],
"env": { "X402_BUYER_PRIVATE_KEY": "0x..." }
}
}
}
Without X402_BUYER_PRIVATE_KEY only the free score_token tool works. Use a
dedicated payer wallet (Base, USDC) — never your main wallet.
Configuration (env)
| Variable | Default | Purpose |
|---|---|---|
PAYFLOWAGENT_API_BASE |
https://payflowagent.net |
Service base URL. |
X402_BUYER_PRIVATE_KEY |
— | Payer wallet key (Base, USDC). Enables paid tools. |
X402_BUYER_RPC |
https://mainnet.base.org |
Payment RPC (optional). |
Reference agent
See examples/screen-bot — polls /v1/screen every few
minutes, de-duplicates, and alerts on new high-score tokens (optional webhook).
Fork it and point it at your own trading logic.
Develop locally
npm install
npm run typecheck
npm run build # emits dist/
npm start # runs the stdio server from source (tsx)
License
MIT — see LICENSE.
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.