MCPLow riskUnclaimed
TWZRD Agent Intelligence
Pre-spend trust for AI agents that buy: check x402 services and product listings before paying.
twzrd-soltwzrd-sol/twzrd-agent-intel
server.json
{
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"name": "io.github.twzrd-sol/twzrd-agent-intel",
"description": "Pre-spend trust for AI agents that buy: check x402 services and product listings before paying.",
"title": "TWZRD Agent Intelligence",
"repository": {
"url": "https://github.com/twzrd-sol/twzrd-trust",
"source": "github"
},
"version": "0.5.11",
"websiteUrl": "https://intel.twzrd.xyz",
"packages": [
{
"registryType": "pypi",
"registryBaseUrl": "https://pypi.org",
"identifier": "twzrd-agent-intel",
"version": "0.5.11",
"transport": {
"type": "stdio"
},
"environmentVariables": [
{
"description": "Signal source: 'artifacts' (your own settlement volume from TWZRD_ARTIFACTS_DIR) or 'bazaar' (live cross-facilitator x402 catalog). Defaults to a static research registry.",
"format": "string",
"name": "TWZRD_SIGNAL_SOURCE"
}
]
}
],
"_meta": {
"io.modelcontextprotocol.registry/publisher-provided": {
"summary": "Pre-spend trust for AI agents that buy things. x402 services: free preflight and merchant_card (wash_flagged refuses), first paid hop GET /v1/intel/quick/{seller_payTo} at 0.001 USDC, optional portable V7 receipts at GET /v1/intel/trust (V5 and V6 still verify). Product listings: the free MCP tool check_listing tests a store product against TWZRD's published listing-claim card (one reference card today) and flags needs_approval when a declared price cannot be backed; get_claim and get_evidence return the card and get_publication returns the Ed25519-signed publication record to verify it offline; get_shopping_check returns the Agent Shopping Check report. Nothing here authorizes spending. TWZRD Bazaar catalog is GET /v1/intel/bazaar/offers — not GET /v1/intel/marketplace (listing overlay, not a bazaar) and not 402 extensions.bazaar."
}
}
}Permissions
DeclaredDetected
Runs code—
pythonInstalls—
pypi:twzrd-agent-intel@0.5.11Runs install scripts—None
NetworkNoneNone
Needs credentialsNoneNone
Outside the workspace—None
Agent tools—None
Checks
Low risk · Nothing worth a warning was found.
Not reviewed by a person · Checked by rules; the model review is not switched on yet.
Versions
- #10.5.11latestOct 7, 2026
TWZRD Agent IntelligenceOpen in Codeg