Security & Testing
twzrd.xyz
This MCP server provides tools for preflight checks, resource evaluation, input verification, and market health probes, likely for ensuring security and readiness of API interactions.
ENDPOINT 1
https://intel.twzrd.xyz/mcp
MCP server metadata
- Name
- twzrd-agent-intel
- Version
- 0.5.9
TWZRD is pre-spend trust for the x402 SERVICE you are about to buy (seller + resource), not a payer-graph explorer. PRIMARY WORKFLOW (use these first): (1) evaluate_x402_resource(resource_url) when you have a URL — fetches 402, extracts seller, preflight; if you need to discover what is callable, use HTTP GET /v1/intel/resources (resource join SOT: listed|live_402 discovery claims separate from settlement trust) — not a new MCP tool; (2) get_merchant_card(wallet) — route on next_action.decision (refuse | insufficient_evidence | no_negative_signal); wash_flagged=true refuses; null means never evaluated (NOT clean); (3) get_readiness_card_tool(seller_wallet|resource) — free decision allow|warn|block + reason_codes + recommended_action + maximum_recommended_spend_usdc (advisory, not legal advice); (4) verify_receipt — offline check of a signed V6 receipt after paid trust. (5) twzrd_watch_add — re-check seller after recheck_after_unix (when watch lane enabled). On block / recommended_action=do_not_pay: do not pay. On warn: respect cap. On allow: proceed only under agent policy. Discovery: prefer HTTP GET /v1/intel/resources (callable catalog + settlement join; stays off the MCP tool list so tool count remains 24). Optional ingested-listing overlay: get_x402_directory. Paid portable proof: GET /v1/intel/trust/{pubkey}?seller_wallet=<payTo> ($0.05 USDC). New here? twzrd_demo_gate runs a zero-setup, no-spend proof of this gate (block path aborts, no wallet, no USDC). get_top_intel_agents is secondary corpus research (who is paying), not the default start path. Streamable-http: Accept application/json, text/event-stream is optimal; plain application/json / */* / missing Accept are accepted (server normalizes). MACHINE RE-CALL: paid receipts carry twzrd_receipt.preimage.{recheck_after_unix, staleness_days, score_decay_model}; re-call trust when due. score_decay_model is 'step:<=7d=1.0,<=30d=0.8,<=90d=0.5,>90d=0.25'. Payer holds USDC for paid calls; gas is sponsored. PUSH RE-CALL (watch lane): after preflight or paid trust, register a watch with twzrd_watch_add(payer_wallet, seller_wallet, webhook_url?) - TWZRD re-checks the seller when recheck_after_unix elapses and POSTs to your webhook when the score/decision materially changes. Poll-only agents omit webhook_url and check twzrd_watch_list(payer_wallet). twzrd_watch_remove(watch_id, payer_wallet) deactivates.
Known tools 24
get_solana_market_visibility_mapReturns the current Solana Market API visibility map (which markets have meaningful on-chain settlement activity and liquidity signals).
Inferred read-onlyget_solana_market_orderbook_depthReturns normalized orderbook depth and liquidity profile for a specific ticker from Solana Market API data.
Inferred read-onlyget_solana_market_shapeReturns market shape / structure signals for a ticker (concentration, venue fragmentation, settlement patterns).
Inferred read-onlyget_solana_market_onchain_trades_summaryReturns recent on-chain trade and settlement activity.
Potential side effectsscore_wallet_for_intelFree discovery: real 0-100 intel score for a wallet from its observed x402 payment history across the broader x402 ecosystem (paid calls, distinct counterparties, volume, recency).
Potential side effectsget_top_intel_agentsLeaderboard of observed payer wallets in the x402 settlement graph, each with its intel score.
Inferred read-onlyget_provider_reputationFree discovery: corpus-backed SELLER reputation for a merchant/provider wallet.
Inferred read-onlyget_merchant_cardFree merchant card: observed inbound payment-graph quality around a Solana receive wallet.
Potential side effectsverify_receiptFree utility: offline-verify a portable v5/v6 trust receipt — the "after you pay" half of the loop.
Potential side effectsget_facilitator_footprintFree discovery: which x402 facilitators a payer has settled through, and how many.
Inferred read-onlyget_counterpartiesFree discovery (capped teaser): the top-N merchants a wallet actually pays, by event count, with per-edge tx_count / total_usdc / first+last timestamps.
Inferred read-onlyscore_wallets_batchFree discovery: score up to 25 wallets in a single call (each via the same transparent model as score_wallet_for_intel).
Inferred read-onlyget_x402_directoryWash overlay on ingested PayAI/CDP/Agentic listings (PayAI not_indexed).
Inferred read-onlytwzrd_demo_gateRunnable, no-spend proof of the TWZRD buyer-side x402 trust gate - discoverable at runtime with no install and no human.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.twzrd-agent-intel]
url = "https://intel.twzrd.xyz/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"twzrd-agent-intel": {
"type": "http",
"url": "https://intel.twzrd.xyz/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: twzrd-agent-intel
Remote MCP URL: https://intel.twzrd.xyz/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"twzrd-agent-intel": {
"url": "https://intel.twzrd.xyz/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"twzrd-agent-intel": {
"type": "http",
"url": "https://intel.twzrd.xyz/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "twzrd-agent-intel",
"transport": "streamable-http",
"url": "https://intel.twzrd.xyz/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Trust Data Available
BuiltWith Trust API v2 evidence for twzrd.xyz was fetched 2026-08-03T16:18:37.469Z and is being refreshed.
twzrd.xyz is assessed as Trusted: Domain has an established technology history spanning over a year.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.