About djd-agent-score
djd-agent-score exposes a reputation scoring API for AI agent wallets on Base as MCP tools. It supports score checks, fraud reporting, blacklist lookups, wallet registration, and related data; some endpoints use x402 micropayments.
Key features
- 01Retrieve basic and full reputation scores
- 02Refresh scores with recent chain data
- 03Submit fraud reports and check blacklist
- 04Register wallets and view leaderboard
- 05Get SVG badges and service health
Use cases
- 01Assess an agent wallet before a transaction
- 02Check a wallet against fraud reports
- 03Register a wallet and display its score badge
MCP support
Exposes the DJD Agent Score REST API as tools for MCP-compatible agents. Some paid tools return x402 payment details for the agent framework to handle.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y djd-agent-score-mcpDJD_BASE_URLBase URL for the DJD Agent Score API (defaults to production)DJD_TIMEOUT_MSRequest timeout in milliseconds (default: 10000)Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
9Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| wallet | string | Yes | Ethereum wallet address (e.g. 0xAbC...123) |
Details
From the project READMEdjd-agent-score-mcp
MCP server for DJD Agent Score — a reputation scoring API for AI agent wallets on Base.
This server exposes the DJD Agent Score REST API as Model Context Protocol tools, so any MCP-compatible agent (Claude, GPT, Gemini, LangChain, etc.) can call scoring endpoints natively.
Tools
| Tool | Endpoint | Cost | Description |
|---|---|---|---|
score_basic | GET /v1/score/basic | Free | Basic score, tier, confidence |
score_full | GET /v1/score/full | $0.10 (x402) | Full dimension breakdown |
score_refresh | GET /v1/score/refresh | $0.25 (x402) | Re-score with latest chain data |
report_fraud | POST /v1/report | $0.02 (x402) | Submit fraud report |
check_blacklist | GET /v1/data/fraud/blacklist | $0.05 (x402) | Check fraud reports |
get_badge | GET /v1/badge/{wallet}.svg | Free | Embeddable SVG badge |
get_leaderboard | GET /v1/leaderboard | Free | Top scored wallets |
register_agent | POST /v1/agent/register | Free | Register wallet with metadata |
health_check | GET /health | Free | System status |
Installation
npm install -g djd-agent-score-mcp
Or run directly with npx:
npx djd-agent-score-mcp
Configuration
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"djd-agent-score": {
"command": "npx",
"args": ["-y", "djd-agent-score-mcp"]
}
}
}
Cursor
Add to .cursor/mcp.json in your project root:
{
"mcpServers": {
"djd-agent-score": {
"command": "npx",
"args": ["-y", "djd-agent-score-mcp"]
}
}
}
Claude Code
Add to your project's .mcp.json:
{
"mcpServers": {
"djd-agent-score": {
"command": "npx",
"args": ["-y", "djd-agent-score-mcp"]
}
}
}
Generic MCP Client (Streamable HTTP)
Start the server in HTTP mode:
TRANSPORT=http PORT=3000 npx djd-agent-score-mcp
Then connect your MCP client to http://localhost:3000/mcp.
Environment Variables
| Variable | Default | Description |
|---|---|---|
DJD_BASE_URL | https://djd-agent-score.fly.dev | API base URL (use http://localhost:3001 for local dev) |
DJD_TIMEOUT_MS | 10000 | Request timeout in milliseconds |
TRANSPORT | stdio | Transport mode: stdio or http |
PORT | 3000 | HTTP server port (only used when TRANSPORT=http) |
Development
git clone <repo-url>
cd djd-agent-score-mcp
npm install
npm run build
npm start
To point at a local API during development:
DJD_BASE_URL=http://localhost:3001 npm start
x402 Payment
Some endpoints require x402 micropayments. When an agent calls a paid tool, the API responds with HTTP 402 and payment instructions. Your agent framework must:
- Detect the 402 response
- Complete the x402 payment (USDC on Base)
- Retry the request with the payment proof
The MCP server surfaces the 402 details in the tool's error response so the agent can handle it.
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.