TWZRD

MCP serverAI & models

twzrd-agent-intel gives an AI a reputation that others can check before they spend with it. The reputation is a pre-spend x402 reputation built from behavior that has actually been observed. Each record comes as a portable signed receipt, so an AI can carry its track record wherever it goes.

Available today. Use it from your connected AI after setup.

After adding it, visit github.com/twzrd-sol/twzrd-trust for the code and details. Your AI can then start building its reputation as its behavior is observed.

Then ask your AI: use TWZRD to get readiness card tool

What your AI can do with it

  • Build a pre-spend x402 reputation from observed behavior
  • Give others something to check before they spend with the AI
  • Record past behavior as portable signed V6 receipts
  • Carry those receipts from one place to another
  • Show a track record based on what actually happened, not claims

Install TWZRD

The server’s own address, for the clients that take one directly. Or connect ahel onceand every client you use reads it from one address, with the account kept on ahel rather than in each client’s config.

  • Claude Code

    claude mcp add --transport http --scope user twzrd 'https://intel.twzrd.xyz/mcp'

    Run it once in your project, then open /mcp to approve any sign-in the server asks for.

  • Claude Desktop

    https://intel.twzrd.xyz/mcp

    Add a custom connector in Settings, paste this address, and approve the sign-in.

  • Cursor

    cursor://anysphere.cursor-deeplink/mcp/install?name=twzrd&config=eyJ1cmwiOiJodHRwczovL2ludGVsLnR3enJkLnh5ei9tY3AifQ==

    Open the link and Cursor adds the server at that address.

  • ChatGPT

    https://intel.twzrd.xyz/mcp

    In Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.

  • Codex

    codex mcp add twzrd --url 'https://intel.twzrd.xyz/mcp'

    Run it once, then sign in with codex mcp login twzrd if the server asks for an account.

From the project's README

As published by twzrd-sol/twzrd-trust in README.md.

Don't let your agent sign blind.
Spend control and counterparty trust for agents paying over x402 on Solana (and Base). Vet the seller before USDC leaves the wallet, cap and ledger every spend, and bind each settled payment to the exact offer it paid for (bind-v1 — verifiable from public chain data). Free preflight → optional paid V7 receipt. Not a wallet. Not a payment network. Not Catena's Agent Commerce Kit — the walkthrough lives in docs/COMMERCE-KIT.md.

Canonical skill (always refresh) • https://intel.twzrd.xyz/skill.md (twzrd-trust 1.13.17) · ClawHub twzrd-trust
Spend-control SDK (npm) • twzrd-x402-gate@0.9.5 + seat x402-solana@3.0.0
Live MCP • https://intel.twzrd.xyz/mcp (streamable HTTP — 24 tools)
Agent contract • https://intel.twzrd.xyz/llms.txt · https://intel.twzrd.xyz/.well-known/agent.json


60-second deterministic free demo

Run this one-line command with no wallet, no API key, and no configuration:

curl -fsS https://intel.twzrd.xyz/v1/intel/demo-gate | jq '{verdict: (.steps[] | select(.name == "block_path") | .verdict), approved: (.steps[] | select(.name == "block_path") | .approved), signerInvocations: (.steps[] | select(.name == "block_path") | .signer_invocations), mode, ok}'

Without jq, run: curl -fsS https://intel.twzrd.xyz/v1/intel/demo-gate

Expected output:

{
  "verdict": "block",
  "approved": false,
  "signerInvocations": 0,
  "mode": "no_spend",
  "ok": true
}

Blocks happen before your signer is invoked (signerInvocations: 0) — zero USDC at risk.


Quickstart

1. Install

npm install twzrd-x402-gate@0.9.5 x402-solana@3.0.0

2. Wrap paid fetches with spend controls

import { twzrd } from "twzrd-x402-gate";

const result = await twzrd.safeFetch("https://merchant.example/paid-endpoint", {
  maxSpend: "0.10",            // per-call cap AND cumulative budget in USD
  allowNetworks: ["solana"],   // allowed settlement networks
  requireOfferBinding: true,   // demand an on-chain verifiable bind-v1 receipt
  pay: async ({ url, paymentRequired, selected }) => {
    // Your existing x402 client signs here — e.g. @x402/fetch + your signer
    return await myWallet.payX402(url, paymentRequired, selected);
  },
});

// On block: result.verdict === "block", result.signerInvocations === 0

3. Or hook an existing client

import { createX402Client } from "x402-solana";
import { createTwzrdBeforePaymentHook } from "twzrd-x402-gate";

const client = createX402Client({
  wallet,
  network: "solana",
  beforePayment: createTwzrdBeforePaymentHook({ refuseWashFlagged: true }),
});

Commerce loop

One path. Install twzrd-x402-gate@0.9.5. Free preflight does not enforce; AutoGate on the pay path does.

  1. Install the gate — npm i twzrd-x402-gate@0.9.5 then installTwzrdAutoGate
  2. Directory — GET /v1/intel/resources (or listDirectoryCallables) — bazaars list; TWZRD sits beside
  3. Preflight — free ReadinessCard + merchant_card wash refuse
  4. Pay only when policy allows — blocks have signerInvocations === 0
  5. Verify — bind-v1 / V7 (optional ACK-Pay VC). No second passport format
  6. Evidence bundle — exportEvidenceBundle / npx twzrd-evidence-bundle
  7. Portable decision receipt — twzrd.payment_decision.v1: what the agent saw, allow | block | warn | unavailable, a reason code and an evidence id, verifiable offline with npx twzrd-payment-decision --verify — spec: docs/payment-decision-v1-spec.md

Refuse-first demo (0 USDC): npx tsx twzrd-x402-gate/examples/commerce-kit.ts
Walkthrough: docs/COMMERCE-KIT.md

Default Protection Sequence

  1. Discover — GET /v1/intel/resources (resource catalog)
  2. Merchant card — GET /v1/intel/merchant_card/{pay_to} (refuse if wash_flagged: true)
  3. Preflight — POST /v1/intel/preflight → ReadinessCard (allow / warn / block)
  4. Optional V7 Receipt — GET /v1/intel/trust/{pay_to} ($0.05 USDC paid receipt)
  5. Pay — sign only when preflight & spend policy allow
# Free preflight (no signup, no wallet)
curl -s -X POST https://intel.twzrd.xyz/v1/intel/preflight \
  -H 'content-type: application/json' \
  -d '{"seller_wallet":"46vMcwuC4sK11sB3gkLhyA7J7GEwfkhn5rFyDtihBwqe","price_usdc":0.01,"agent_intent":"preflight"}'

Packages & References

PackagePinDescription
twzrd-x402-gate@0.9.5Spend-control SDK (twzrd.safeFetch) + pre-sign gate hooks
x402-solana@3.0.0Compatible Solana client seat for the pre-payment gate
twzrd-receipt-verifier@^1.4.0Standalone offline verifier for Ed25519 V5/V6/V7 receipts
twzrd-mcp-server@0.5.2Local spend-capped auto-pay client (6 tools)
twzrd-log-verifierlocal 0.2.1Offline Receipt Transparency log verifier — inclusion/consistency proofs, key rotation, split-view pinning (spec)

Tools it offers (28)

What this server listed when ahel dialed its public endpoint in Sep 2026, with no key and no account of yours. The names are the server’s own.

  • get_readiness_card_tool
  • evaluate_x402_resource
  • low_level_preflight
  • verify_root_inputs
  • get_solana_market_status
  • score_wallet_for_intel
  • get_top_intel_agents
  • get_provider_reputation
  • verify_x402_settled_claim
  • submit_contribution_claims
  • get_poec_score
  • get_merchant_card
  • is_wash_fleet
  • verify_receipt
  • get_facilitator_footprint
  • get_counterparties
  • score_wallets_batch
  • compare_wallets
  • get_x402_directory
  • twzrd_watch_add
  • twzrd_watch_list
  • twzrd_watch_remove
  • twzrd_demo_gate
  • get_claim
  • get_shopping_check
  • get_evidence
  • get_publication
  • check_listing

Signals

Forks
1
Last commit
Sep 2026
Weekly downloads
20
Weekly_downloads
1k weekly_downloads
Advanced
Delivery
twzrd-agent-intel MCP server → your ahel connector (mcp.ahel.ai) → your AI.
Item type
mcp-server
Key
xyz-twzrd-intel-twzrd-agent-intel
Source
github.com/twzrd-sol/twzrd-trust
Hosted endpoint
https://intel.twzrd.xyz/mcp