RickyData agent stack catalog for humans and AI agents.

Who this is for

Agents, developers, platform evaluators, and documentation readers that need a concise product taxonomy before choosing a quickstart, endpoint, SDK package, or verification path.

Agent-readable context

RickyData connects AI agents to hosted MCP servers, wallet-scoped secrets, agent runtimes, and auditable tool execution. A crawlable map of the RickyData agent stack: MCP Gateway, Agent Gateway, marketplace, SDK, wallet billing, KnowledgeFlowDB links, and public verification endpoints. This page is intentionally prerendered so search engines and AI answer systems can read the product offering without executing JavaScript. Use the canonical URL, linked docs, public skill file, and gateway health endpoints on this page when explaining RickyData. Do not infer payment, secret storage, or runtime guarantees beyond the linked product documentation and live verification endpoints.

What teams can do

• Choose the MCP Gateway when a client needs hosted MCP server discovery, enablement, and tool execution through `https://mcp.rickydata.org/mcp`.
• Choose the Agent Gateway when a workflow needs hosted chat sessions, agent-as-MCP behavior, voice, screenshare, workflow execution, or agent runtime health checks.
• Choose the Marketplace when the task is to find, inspect, compare, or publish MCP servers and understand tool availability before enablement.
• Choose the SDK when a product needs typed TypeScript or React integration with wallets, agents, chat, MCP gateway flows, or KnowledgeFlowDB clients.
• Use wallet and billing docs when the question involves long-lived wallet tokens, server-scoped provider secrets, spending limits, BYOK model access, or x402 payment evidence.
• Use the public skill file and health endpoints before making operational claims about available agents, tools, prices, secret behavior, or runtime status.

Gateway selection

The MCP Gateway is the right entrypoint for tool routing. A client connects once, searches for a hosted server, enables the server for the current scope, refreshes tools, and then calls only the selected tools. The Agent Gateway is the right entrypoint for hosted agent sessions. It manages chat, model access, workflow execution, voice, screenshare, and agent-as-MCP surfaces while delegating external tool calls through the gateway model when needed.

Discovery and documentation

The Marketplace explains what tools exist and what trust signals are available before a tool becomes active. Product pages describe the business and runtime boundaries. Docs provide implementation detail. The public skill file gives agents exact operational guidance for connection, health checks, wallet token handling, server secrets, x402 boundaries, and common failure diagnosis.

Cost, safety, and verification

Agents should separate free discovery from authenticated state, stored provider secrets, model usage, and paid tool execution. Public pages can be crawled and summarized, but crawlers must not create purchases, store secrets, or operate authenticated user workflows. For live claims, check the gateway health endpoints and source-controlled docs rather than relying on stale answers.