{
  "markdown": "# provenance-mcp\n\n**Check the wash-traffic risk of Algorand x402 endpoints before your agent pays them.**\n\n📊 **[The x402 Trust Index](https://apeirontrade.github.io/provenance-site/)** — our free public\nleaderboard: weekly Bazaar Wash Report + resale-authorization audits for 38 API brands.\n\nRoughly half of x402 \"agentic payment\" activity is artificial — self-dealing loops,\nfresh-wallet farms, metronomic bots. Provenance reads the chain and tells your agent\nwhether an endpoint's revenue is **organic or fabricated**, so it can decide *before*\nsending USDC.\n\n## Tools\n\n- **`check_endpoint_risk(address)`** — free quick verdict for any Algorand endpoint\n  payTo address: risk level (`low/medium/high/critical`), 0–100 score, and the\n  on-chain red flags (distinct-payer count, self-dealing payout loops, wallet ages,\n  timing regularity, funding concentration).\n- **`provenance_service_info()`** — service + paid-tier info.\n\nDeep forensics are x402-paid on the same API: `/score` $0.05 · `/report` $0.50\n(full 8-signal grade + facilitator drift) · `/diligence` $5.00.\n\n## Install\n\n**Claude Code**\n```bash\nclaude mcp add provenance -- npx -y provenance-mcp\n```\n\n**Claude Desktop / any MCP client** (`mcpServers` config):\n```json\n{\n  \"mcpServers\": {\n    \"provenance\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"provenance-mcp\"]\n    }\n  }\n}\n```\n\nThen ask your agent: *“check the wash risk of Algorand endpoint \\<ADDRESS\\>”*.\n\n## How it works\n\nThe hosted Provenance engine indexes USDC (ASA 31566704) payments on Algorand\nmainnet, enriches payer wallets (age, first funder, asset diversity, rekey\nauth-addr), clusters them (union-find over funding + shared-key links), and runs\n8 wash-detection signals. Scores are point-in-time snapshots, anchored on-chain\nfor tamper-evidence. Methodology: signals, not accusations — a high score means\nthe revenue pattern is consistent with self-dealing, not that the operator is\nguilty of anything.\n\n- Env: `PROVENANCE_API_URL` to point at a different Provenance deployment.\n- Free tier: 30 checks/hour/IP.\n\n## Guard your x402 client directly\n\nBuilding an agent that pays over x402? [`provenance-guard`](https://github.com/apeirontrade/provenance-guard)\nwraps any x402-paying fetch and runs this same check automatically **before any\nmoney moves** — one line, zero dependencies:\n\n```typescript\nimport { createGuard } from \"provenance-guard\";\nconst guarded = createGuard().guardedFetch(fetchWithPayment);\n```\n\nMIT · Provenance — the trust layer for machine-payable endpoints.\n",
  "bytes": 2516,
  "sha": "f452de8f34fb3f25933f1ea38f1861f448e583d9a867995336b56303dd03d323",
  "repo_slug": "apeirontrade/provenance-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_apeirontrade_provenance_mcp_52a2d4e5/readme"
}