twzrd-agent-intel 0.5.3

Trust + receipt layer that Solana agents call before and after paying over x402 — free preflight readiness cards, paid signed trust receipts, and a wash/Sybil-resistant agent reputation corpus. MCP + HTTP.

twzrd-agent-intel

The trust + receipt layer that Solana agents call before and after paying over x402.

Before an autonomous agent pays a stranger's API, it should be able to answer one question: should I pay this, and what proof will I get? twzrd-agent-intel answers it. Free preflight readiness cards score any x402 resource on a wash/Sybil-resistant reputation corpus; a paid trust endpoint returns a portable, offline-verifiable signed v6 receipt. Live on Solana mainnet.

Where this sits

Autonomous agents hold wallets and pay strangers over x402 — no human gut-check. At pay time a wash seller looks identical to an honest one. TWZRD is the wedge that scores the seller before the agent signs.

  AGENTS (spend)   70k payers · 866 real shoppers   (ecosystem-observed — NOT TWZRD revenue)
        │  "should I pay this seller?"  ── no reputation rail exists
        v
  ┌────────────────────  TWZRD TRUST LAYER  ────────────────────┐
  │  POST /v1/intel/preflight → decision = allow | warn | BLOCK │
  │                             + trust 0-100 + caveats         │
  │  CORPUS moat (cross-facilitator x402 graph) + paid v6 receipt│
  │  CONSUMABLE: plugin-trustgate (npm) · MCP · PyPI · verifier  │
  └──────────────────────────────┬──────────────────────────────┘
          allow / warn            │             BLOCK
                │                 │               │
                v                 │               v
  RAILS THAT SETTLE (PayAI · openfacilitator · x402)    ╳ agent ABORTS
        │
        v
  SELLERS    honest hub      wash-shaped tail        controlled rig
             7uh2ibD1        34w53Ukh                FTNMk
             → WARN          → BLOCK                 → BLOCK
             (clean)         (91% captive; a real    (test fleet)
                              shopper paid it $7.9k)

Live proof of organic intercept. Flagged seller 34w53Ukh (real, non-TWZRD; wash_flagged, 91.4% captive payers, a real shopper paid it ~$7,957) → decision=block (trust 30): an agent running the guard aborts. Clean control 7uh2ibD1 → warn (trust 45): it proceeds. The gate discriminates on live, unfunded sellers.

Honest frontier. Trust gates the buyer preflight today (proven, 100% agent-driven). The settle-side hook (onBeforeSettle) is next. One real agent installing the guard = demand unlocked.

Try it now (no install, no signup)

curl -s -X POST https://intel.twzrd.xyz/v1/intel/preflight \
  -H "Content-Type: application/json" \
  -d '{
    "seller_wallet": "6EF8rrecthR5Dkzon8Nwu78hRvfCKubJ14M5uBEwF6P",
    "agent_intent": "swap_quote"
  }'

Returns a ReadinessCard with decision (allow / warn / block), trust_score, can_spend, caveats, and the path to the paid deep-dive receipt.

Install

pip install twzrd-agent-intel

Wire into Claude Code / Claude Desktop / Cursor (60 seconds)

Add to your MCP config and restart. The remote server runs the live large cross-facilitator corpus — no env vars, no local server, no configuration:

{
  "mcpServers": {
    "twzrd-agent-intel": {
      "type": "streamable-http",
      "url": "https://intel.twzrd.xyz/mcp"
    }
  }
}

After restart your agent sees 17 tools. The most useful one to call first:

get_readiness_card_tool(seller_wallet="6EF8rrecthR5Dkzon8Nwu78hRvfCKubJ14M5uBEwF6P")

That's the full install. No database, no keypair, no USDC needed for the free tools.

18 MCP tools

Free preflight + discovery (no payment, no auth):

• get_readiness_card_tool — primary ReadinessCard
• dexter_preflight — lower-level preflight + spend recommendation
• score_wallet_for_intel — wallet intel score
• get_top_intel_agents — agent leaderboard discovery

Free corpus reputation + receipts:

• get_provider_reputation — inbound corpus reputation for a seller/merchant wallet
• is_wash_fleet — circular-flow / wash-fleet check on a wallet
• get_facilitator_footprint — which x402 facilitators a payer settled through
• get_counterparties — capped teaser: top merchants a wallet pays (limit ≤ 25)
• score_wallets_batch — score up to 25 wallets in one call
• compare_wallets — side-by-side intel for two wallets
• verify_receipt — offline v5/v6 receipt verification (recompute leaf + check Ed25519 sig)
• verify_root_inputs — independently recompute a published attention root and assert against the on-chain commitment
• evaluate_x402_resource — evaluate whether a resource server deserves payment: receipt pipeline quality, guard coverage, and spend recommendation

Solana market intel (free over MCP; $0.03 USDC each over HTTP x402):

• get_solana_market_visibility_map
• get_solana_market_orderbook_depth
• get_solana_market_shape
• get_solana_market_onchain_trades_summary
• get_solana_market_status

The paid trust receipt (GET /v1/intel/trust/{pubkey}, 0.05 USDC over x402) is also available over HTTP with a portable signed v6 receipt you can verify offline.

HTTP API

# Free preflight (no payment required)
curl -s -X POST https://intel.twzrd.xyz/v1/intel/preflight \
  -H "Content-Type: application/json" \
  -d '{"seller_wallet": "<pubkey>", "agent_intent": "swap_quote"}'

# Paid trust receipt (0.05 USDC over x402 — use an x402-capable client)
curl -s https://intel.twzrd.xyz/v1/intel/trust/<pubkey>
# → 402 Payment Required with payment requirements if no x402 header

# Free sample receipt for offline verify testing
curl -s https://intel.twzrd.xyz/v1/receipts/example

• OpenAPI: https://intel.twzrd.xyz/openapi.json
• Agent card: https://intel.twzrd.xyz/.well-known/agent-card.json
• MCP card: https://intel.twzrd.xyz/.well-known/mcp-server.json

Self-hosting

Note: Running twzrd-agent-intel-mcp locally serves from a small static research registry by default — not the live large cross-facilitator corpus. Use the remote MCP above for real data. Self-host only if you need to run behind a firewall or extend the server.

# Local MCP stdio (static demo data by default)
twzrd-agent-intel-mcp

# Local HTTP server
uvicorn twzrd_agent_intel.server_http:app --port 8001

Point a self-hosted instance at live data with environment variables:

TWZRD_SIGNAL_SOURCE	What it does
artifacts	Aggregate your own settlement volume from TWZRD_ARTIFACTS_DIR
bazaar	Pull the live cross-facilitator x402 catalog (CDP Bazaar)

What makes the score trustworthy

• Wash/Sybil-resistant: circular-flow- and wash-resistant scoring over a large cross-facilitator corpus.
• Honest basis: trust components are renormalized (score_version intel_renorm_v1) so arbitrary wallets aren't penalized for lacking TWZRD-native execution history.
• Verifiable: every paid response carries a signed v6 receipt you can verify offline at /v1/receipts/verify without trusting our server.

More TWZRD surfaces

• Verify a live receipt offline in one command (TypeScript SDK, no wallet):

  npx @wzrd_sol/sdk
  

• OpenClaw agents: install the skill that wraps this API into a pre-payment check:

  clawhub install twzrd-trust
  

License

MIT

• Public leaderboard: https://twzrd.xyz/leaderboard