What does the score mean?
Scores range 0–100, with tiers: Elite (90+), Trusted (75–89), Established (50–74), Emerging (25–49), Unverified (0–24). Higher scores come from more USDC transaction history and verified identity.
@jacobsd32-cpu
基本信息
On-chain reputation scoring API for AI agent wallets on Base, monetized via x402 micropayments. Scores wallets 0-100 across reliability, viability, identity, behavior, and capability dimensions.
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
DJD Agent Score is a trust and governance layer for agent wallets on Base. It screens counterparties before an agent sends funds or fulfills a paid x402 request, providing a reputation score (0–100) based on USDC transaction history and identity signals.
Install the MCP server via npm i djd-agent-score-mcp and connect it to any MCP client (Claude, Cursor, Windsurf, Codex). Use the free tier for basic lookups (10/day) or authenticate with an API key for higher volume. The REST API and TypeScript/Python SDKs are also available.
x402-agent-score).Scores range 0–100, with tiers: Elite (90+), Trusted (75–89), Established (50–74), Emerging (25–49), Unverified (0–24). Higher scores come from more USDC transaction history and verified identity.
The free tier allows 10 basic score lookups per day without an API key or payment.
The score uses five dimensions: Payment Reliability (30%), Economic Viability (25%), Identity (20%), Behavior (15%), and Capability (10%). Weights adapt over time based on outcome correlation. The model also includes sybil detection, gaming detection, and fraud report penalties.
Paid endpoints (USDC on Base via x402) include full score breakdown, score refresh (bypasses cache), historical data, fraud blacklist checks, and certification applications. Prices range from $0.02 to $99.00.
Yes. High-volume users can obtain an API key (`Bearer djd_live_…`) and requests are counted against a monthly quota instead of requiring individual x402 payments.
MCP-native LLM councils for debates, juries, blind panels, voting, refinement, and custom multi-model deliberation.
TruVerifAI's Panel Review is the guardian agent for AI's highest-stakes coding decisions: four frontier models argue over an AI coding agent's riskiest designs, diffs, and commits before they execute, with local review g
AON MCP connects AI agents to real, buyable products and services with live pricing and tracked links—enabling builders to earn developer revenue share from attributed clicks and conversions.
早起鸟儿喊真人验真 is a remote MCP server available at http://121.40.18.232.
HeyLead: AI agent for LinkedIn outreach. Finds the right people, writes in your voice, follows up and handles replies, from Claude Code, Cursor, any MCP client or a web dashboard.
评论