luminarylane-app-mcp.yml
Luminary Lane operates ONE remote Model Context Protocol server, https://mcp.luminarylane.app/mcp (Streamable HTTP, Express-hosted, server name luminary-mcp-server v1.0.0), that exposes the Lane workspace — brands, brand foundation, traction and presence plans, the action approval queue and integrations — to MCP clients. It is authenticated: an anonymous initialize or tools/list returns 401 invalid_token with an RFC 9728 resource_metadata pointer, and an X-API-Key header is accepted as an alternative credential (keys prefixed ll_mcp_, generated at app.luminarylane.app/profile/api-keys). The anonymous /health endpoint publishes the 46 registered tool NAMES, so the tool list below is real but the input schemas are gated. Separately, the company publishes 14 open-source stdio MCP servers on npm/PyPI that wrap third-party marketing platforms (LinkedIn, X, Bluesky, Facebook, Instagram, WordPress, Sanity, Gmail, Fathom, GA4, Search Console, fal.ai, a fact-checker and a design-style service); those are catalogued in packages/ and do not reach Luminary Lane data.
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
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.