APIs, tools and merchants AI agents can actually use. Every badge is probe-backed, never self-asserted.
Unified model endpoint with failover, spend limits, and observability, wired into the AI SDK
AuthKit, Connect, and MCP auth — OAuth flows, scoped tokens, and bot detection for agent access
Open HTTP 402 standard for per-request stablecoin payments, now at v2 and governed by the x402 Foundation
Thousands of app actions exposed to agents through a hosted MCP endpoint, no per-app integration work
Temporal knowledge-graph memory (Graphiti) with bi-temporal validity, so agents can query what was true when
Open protocol using signed mandates so agents can transact within user-defined limits, with x402 and card rails
Open protocol for agent-to-agent discovery, task delegation, and streaming updates across vendors
Session replay, cost tracking, and failure analysis purpose-built for agent runs
Structured records over REST with a remote MCP server agents can read and write
Blockchain node and data APIs — transfers, tokens, NFTs, and webhooks — payable per request over MPP
Commission-free US stocks, options, and crypto brokerage API with a free paper-trading environment
Flight, hotel, and destination content APIs with self-serve keys and a free test environment
Managed browsers for agents with persistent authenticated profiles and proxy handling
Work graph — tasks, projects, and portfolios — over REST and a remote MCP server
Speech recognition, diarization, and audio intelligence models via API
Jira issues and Confluence pages over REST and a remote MCP server
Agent payments platform wrapping x402 wallets, per-call billing, and a hosted tool marketplace agents can spend against
Token vault, async user approval, and Cross App Access for agents calling third-party APIs
Open remote MCP server over AWS documentation, API references, and architectural guidance
Dedicated deployments and autoscaling inference for open and custom models
Same query as JSON: /api/v1/services?page=4Add to Claude Code:claude mcp add botfriendly …