AUX Evidence and Certification
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Documentation
Documentation link · transport none
Tools
aux_certification_profiles— Discover live AUX certification profiles and select the bounded consequential-action contract before submitting evidence.aux_certification_attempt— Create or reuse a deterministic durable certification attempt. AUX automatically retries SOURCE_TEMPORARILY_UNAVAILABLE with bounded backoff and exposes a polling status URL.aux_sanctions_evidence— Resolve bounded official OFAC name-screening evidence directly from Treasury source files.aux_domain_identity_evidence— Resolve registered-domain identity using IANA RDAP plus HTTPS domain-control evidence.aux_source_attestation— Resolve a private evidence source's published trust document and verify its signed attestation before AUX applies it to certification.aux_business_identity_evidence— Independently resolve a legal entity against live GLEIF data and return a signed evidence bundle when the identity is exact and current.aux_evidence_verify— Verify an AUX signed evidence bundle and its integrity commitments.aux_certification_policy_check— Verify a portable AUX certification and apply a downstream consumer policy without executing the underlying action.aux_domain_certification_policy_check— Resolve a consumer's published AUX acceptance policy from its HTTPS domain and evaluate a signed AUX certification.aux_certified_agent_handoff— Create a signed non-executing agent-to-agent handoff only after the recipient domain's independently resolved policy accepts a valid AUX certification.aux_handoff_consumption— Authenticate the intended recipient, atomically consume a verified handoff once, and return a signed receipt with action_executed=false.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.