KYA agent identity verification and trust scoring for autonomous A2A networks
KYA agent identity verification and trust scoring for autonomous A2A networks. This MCP server acts as a broker/observer layer for KYC/AML screening within Hive Civilization’s Model Context Protocol, providing identity checks and trust scoring to enable compliant autonomous agent interactions.
🛠️ Key Features
KYC/AML screening integration for autonomous agents
Trust scoring as a municipal layer in MCP workflows
Broker/observer role within the Hive MCP gateway
Exposes a readme excerpt and project metadata for quick overview
🚀 Use Cases
Identity verification for autonomous A2A transactions
Compliance gating in agent commerce scenarios
Observability and risk assessment within model-context exchanges
⚡ Developer Benefits
Clear MCP integration point for KYC/AML checks
Lightweight broker/observer abstraction
Readme-excerpt provides quick onboarding context
⚠️ Limitations
Data in readmeExcerpt is partial; real health endpoints and integration details should be consulted via the gateway
Specific implementation details and configuration options are not included in the provided excerpt
Hive Agent KYC is a broker/observer layer. It routes screening requests to third-party providers and surfaces public sanctions list matches. It is not a regulated money-services business, does not make custody, lending, or transaction-permitting decisions, and does not issue compliance attestations on behalf of regulated entities. Final compliance determinations remain with the requesting agent and its operator.
This disclaimer is also surfaced verbatim in every tool's response payload, in /.well-known/agent.json, and in the JSON-LD description.
What this is
hive-mcp-agent-kyc is a Model Context Protocol (MCP) server that any MCP-compatible client (Claude Desktop, Cursor, Manus, agent runtimes) can call to:
Route a blockchain address screening request to one of three third-party KYC/AML providers — Chainalysis, TRM Labs, or Elliptic — and return the provider's risk score and flags verbatim (no enrichment, no Hive scoring layer).
Check public sanctions list matches against the OFAC SDN list and the FATF high-risk-jurisdiction lists.
Read back an audit-log entry for a prior query (DID + timestamp + provider + result code only — no PII).
What this does not do:
It does not hold custody of any KYC documents.
It does not make a final allow/deny determination on a transaction.
It does not issue an attestation that a person/entity is "KYC'd by Hive".
It does not operate as a money-services business.
The purpose is to be the CLEAN-MONEY gate primitive that other Hive surfaces (Vault, Trade, Swap, Treasury) can call before settling. Compliance determinations remain with the calling operator.
Protocol: MCP 2024-11-05 over Streamable-HTTP / JSON-RPC 2.0
Transport: POST /mcp
Discovery: GET /.well-known/mcp.json, GET /.well-known/agent.json
Health: GET /health
Settlement: real x402 — USDC on Base L2 to wallet 0x15184bf50b3d3f52b60434f8942b7d52f2eb436e. No mock. No simulated.
Backend status: provider partnership keys pending — agent_kyc_screen_address returns 503 with backend_pending: true until configured. Public list tools (OFAC, FATF) return real data today.
Brand gold: Pantone 1245 C / #C08D23
Tools
Tool
Cost
Description
agent_kyc_screen_address
$0.10 USDC (Base)
Route screening request to Chainalysis / TRM Labs / Elliptic. Returns provider response verbatim. 503 backend_pending until keys configured.
agent_kyc_check_ofac_list
free
Check identifier against OFAC SDN public list. Cached 24h.
agent_kyc_check_fatf_list
free
Check ISO-3166 country code against FATF Call-for-Action and Increased-Monitoring lists.
agent_kyc_query_status
free
Read prior audit-log entry by query_id. Returns DID + timestamp + provider + result code + address hash. No PII.
When no key is set, agent_kyc_screen_address returns 503 backend_pending. The OFAC and FATF tools work without keys.
Settlement
Real x402 rails. The screening tool quotes:
code
recipient : 0x15184bf50b3d3f52b60434f8942b7d52f2eb436e
chain : Base L2
asset : USDC
amount : $0.10 USDC per screen call
No mock. No simulated. No testnet pretending to be mainnet. While the screening backend is in backend_pending, no charge is applied — the x402 quote is informational so calling agents can pre-flight payment configuration.
Hive doctrine context
This server is the CLEAN-MONEY gate primitive in the Hive Civilization three-gate doctrine (NEED + YIELD + CLEAN-MONEY). Any other Hive surface that touches settlement is expected to call agent_kyc_screen_address and the public-list tools before clearing.
It is intentionally a thin broker: enrichment, scoring, and final decision remain with the third-party provider and the operator, respectively. Hive does not become a regulated MSB by routing.