kraken-technologies-mcp.yml
Kraken names MCP on two separate surfaces and only one of them is real today. The Open Kraken "AI access layer" — MCP gateways that let a licensee's AI agents orchestrate approved actions inside Kraken — is announced and "gradually released", with no server URL, no tool list, no scope model and no transport published; mcp.kraken.tech does not resolve in DNS. The one MCP configuration Kraken actually publishes is for its Tako design system: a documented, anonymously usable stdio setup that points the community `storybook-mcp` server at Kraken's own PUBLIC Storybook index, so an IDE assistant can read Tako component documentation while you code. That config is first-party published and verified live; the server binary itself is third-party.
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.
Descriptor
Candidate descriptor · transport
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.