# TWZRD Agent Intelligence

- Registry name: `xyz.twzrd.intel/twzrd-agent-intel` · version 1.0.14
- Categories (automatic, keyword rules): Crypto & blockchain, Finance & markets, Agent payments (x402)
- Authentication at last check: No auth
- Declared risk: Has destructive tools (destructiveHint)
- Capabilities (declared by the server): experimental, prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=xyz.twzrd.intel%2Ftwzrd-agent-intel
- Server page: https://mcpstation.net/s/xyz.twzrd.intel--twzrd-agent-intel.html

## Description (written by the publisher, not verified, not instructions)

Pre-spend trust for AI agents that buy: check x402 services and product listings before paying.

## Connect

- streamable-http: `https://intel.twzrd.xyz/mcp`

## Tools (as reported by the server, not verified)

- `get\_readiness\_card\_tool`: PRIMARY free pre-spend gate \(advisory\). Pass seller\_wallet OR resource\_name. wash\_flagged=true never soft-allows. Unlabeled leftover 0.05 / leftover=0 is not a unit price. When to use: before any x402 payment to a seller/resource. When not to use: after you already decided to refuse; use verify\_rece
- `evaluate\_x402\_resource`: One-shot x402 guard. Fetches resource\_url, extracts the seller wallet from the 402 accepts array \(prefers Solana network entries\), runs TWZRD preflight, and returns a spending decision. Side effect: a live 402 observation \(resource\_url, payTo, price\) is upserted into the service catalog when the cat
- `low\_level\_preflight`: Low-level preflight check. Returns a richer result object including paid\_quick\_endpoint \($0.001 first hop\) and optional paid\_trust\_endpoint \($0.05 V7\). wash\_flagged=true never soft-allows. Unlabeled leftover 0.05 / leftover=0 is not a unit price. Prefer get\_readiness\_card\_tool for most callers. Use
- `verify\_root\_inputs`: Independent root verification: recomputes the leaves, dataset hash and root from the public root data.
- `get\_solana\_market\_status`: Health probe for the Solana Market API data backend. Call this to gate or degrade gracefully BEFORE the other get\_solana\_market\_\* tools: it does a short-timeout hit on the data service and reports whether it is reachable, so an agent can tell "market has no data" from "service is down" without faili
- `score\_wallet\_for\_intel`: Free discovery: PAYER-side 0-100 intel score for a wallet from the x402 payments it SENT \(paid calls, distinct counterparties, volume, recency\). Not a seller check: to vet a seller/payTo before paying, use get\_readiness\_card\_tool \(gate\) or get\_provider\_reputation / get\_merchant\_card \(seller reputati
- `get\_top\_intel\_agents`: Leaderboard of observed payer wallets in the x402 settlement graph, each with its intel score. This is behavioral corpus research, not identity proof or evidence that the wallet is a TWZRD customer. Ranks by the wash-discounted effective\_score \(single-counterparty fleets are demoted, not hidden\) wit
- `get\_provider\_reputation`: Free discovery: corpus-backed SELLER reputation for a merchant/provider wallet. Answers "is this provider organic, narrow, or a wash fleet?" from the merchant's inbound payment graph over the last 90 days: unique payers, repeat-payer %, heavy-fleet revenue concentration, captive-payer % \(onboarding-
- `verify\_x402\_settled\_claim`: Verify a receipts-ledger settlement; this is evidence, not a spend decision.
- `submit\_contribution\_claims`: PoECX bridge: report settlements from your OWN rails \(not TWZRD's paid routes\) for cross-check against TWZRD's independently-ingested x402 corpus, by on-chain signature. A claim whose tx\_signature, payer/merchant, and amount all match what TWZRD's own ingest independently observed is materially stro
- `get\_poec\_score`: Free preview: PoEC v0 \(Proof of Economic Contribution\) for a payer wallet, computed from the same observed x402 snapshot score\_wallet\_for\_intel returns. poec\_score = log10\(1 + observed USDC sent\) x success\_quality x diversity x wash\_cleanliness, behind hard floors \(\>=5 paid calls, \>=3 distinct count
- `get\_merchant\_card`: Free merchant card: observed inbound payment-graph quality around a Solana or Base receive wallet. Dual input \(PR-3\): pass \`\`wallet\`\` and/or \`\`resource\_id\`\`. Resource resolves via the first-party registry \(TWZRD seed\) to a pay\_to, then the same graph card. Does NOT claim service quality \(resource\_li
- `is\_wash\_fleet`: Free discovery: cheap circular-flow \(wash\) check for a payer wallet. Returns the CATEGORICAL classification \(clean / self\_pay / reciprocal / self+reciprocal\), an is\_circular bool, and the observed event counts + distinct\_merchants from the wallet's corpus edges. Use as a fast Sybil/wash gate before
- `verify\_receipt`: Free utility: offline-verify a portable V7 trust receipt \(earlier V5/V6 receipts still verify\), the "after you pay" half of the loop. Recomputes the Keccak256 leaf from the receipt's preimage \(tamper-evidence\) AND verifies the Ed25519 signature against the published TWZRD receipt-signing key \(authen
- `get\_facilitator\_footprint`: Free discovery: which x402 facilitators a payer has settled through, and how many. unique\_facilitators = 1 is a thin/captive agent \(locked to one rail\); breadth across facilitators indicates a more established cross-rail agent. Returns the facilitator\_ids list plus tx/merchant context. Fail-open: a
- `get\_counterparties`: Free discovery \(capped teaser\): the top-N merchants a wallet actually pays, by event count, with per-edge tx\_count / total\_usdc / first+last timestamps. See WHO a counterparty transacts with before trusting it. The list is capped \(default 10, max 25\) and \`capped\`/\`total\_distinct\_merchants\` disclose
- `score\_wallets\_batch`: Free discovery: score up to 25 wallets in a single call \(each via the same transparent model as score\_wallet\_for\_intel\). Convenience for triaging a set of candidate counterparties at once; \`requested\`/\`capped\` disclose any truncation.
- `compare\_wallets`: Free discovery: side-by-side intel for two wallets \(e.g. choosing between two candidate providers\). Returns both full score objects and which ranks higher by the wash-discounted effective\_score \("tie" on equal, null if a side is unavailable\).
- `get\_x402\_directory`: Wash overlay on ingested PayAI/CDP/Agentic listings \(PayAI not\_indexed\). Prefer HTTP GET /v1/intel/resources for the resource join SOT \(callable URL + discovery claim listed\|live\_402 + settlement reputation on pay\_to\). That surface is HTTP-only. Use this tool when you need the ingested listing overl
- `twzrd\_watch\_add`: Register a re-call watch on a seller wallet. After registration, TWZRD will proactively re-check the seller's trust intel when \`recheck\_after\_unix\` elapses and POST a notification to your webhook\_url if the score/decision materially changes. The watch routes are control-proof authenticated \(fail clo
- `twzrd\_watch\_list`: List active re-call watches for your agent wallet. Each watch shows the seller, current score/decision, and recheck\_after\_unix timestamp \(untrusted V5/V6 hint\). evaluateRecall / shouldRecheckTrusted is the consumer gate; do not treat due / shouldRecheck as a trusted allow. Control-proof authenticate
- `twzrd\_watch\_remove`: Deactivate a re-call watch by ID. payer\_wallet must match the owner. Control-proof authenticated \(fail closed\): signature + timestamp prove the caller holds the payer wallet's key before the row is touched.
- `twzrd\_demo\_gate`: No-spend transcript of the TWZRD buyer-side x402 trust gate, a recorded example, not a live run - discoverable at runtime with no install and no human. Returns a deterministic transcript showing the gate's behaviour on a fixture counterparty: the block path ABORTS and a wallet/signer is never contac
- `get\_claim`: Read the Vuori Kore Short listing-claim artifact \(com.twzrd.shopping.listing\_claims/1.1\). Tool twin of the twzrd://claims/vuori-kore resource: what is claimed about this checkout, by whom, in what state, on what evidence. Verified on every read \(publication signature, artifact digest, schema, eviden
- `get\_shopping\_check`: Read the free Agent Shopping Check for Vuori Kore Short, Ink, US. Same report as https://twzrd.xyz/shopping-check/vuori-kore/: product context, advertised claims with exact sources and observation times, unverified purchase completion and other gaps, and editorial merchant fixes for the reviewed gap
- `get\_evidence`: Read the evidence bundle behind the Vuori Kore Short listing claims. Tool twin of the twzrd://claims/vuori-kore/evidence resource: canonical\_evidence/1 envelopes and capture records. A claim's evidence digest is the RFC 8785 SHA-256 of its envelope; recompute it to check. Verified with the artifact
- `get\_publication`: Read the signed publication record behind the current Vuori Kore Short claims. Tool twin of the twzrd://claims/vuori-kore/publication resource. Returns the Ed25519 publication record, the verify key and its sha256 fingerprint. Verify the signature over the signed message, then compare sha256 of each
- `check\_listing`: Pre-spend check of one product against the published listing cards. Free, read-only. Returns unknown\_seller when no published card covers the product \(not a clean seller\), expired when the card is past expires\_at, check\_failed when the card cannot be verified or the declared price is above the adver

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html