rosentic-com-mcp.yml
Rosentic ships MCP two ways and they are different products. (1) Rosentic Remote — a hosted Streamable-HTTP endpoint at https://api.rosentic.com/mcp, live since 2026-07-23 per the provider's changelog, behind OAuth 2.1: an anonymous POST of initialize or tools/list returns HTTP 401 with a JSON-RPC error -32001 "Authentication required" (data.error.code AUTH_REQUIRED) and a WWW-Authenticate header of Bearer resource_metadata="https://api.rosentic.com/.well-known/oauth-protected-resource/mcp", scope="rosentic:remote:read" — the RFC 9728 discovery chain, which resolves to an RFC 8414 authorization server on the same host with PKCE S256 and dynamic client registration (both documents captured in well-known/). The live tool schemas are therefore auth-gated; the three remote tools below come from the provider's own MCP page and llms.txt, names and descriptions only. (2) rosentic-mcp — a local stdio server on PyPI (0.2.9, released 2026-09-05, FastMCP-based, Python 3.11+) exposing nine tools, six fully offline against a local checkout, three reading the dashboard API; it needs the engine container ghcr.io/rosentic/rosentic-engine (Docker) or a local engine path. The same package is the MCP server the Cursor plugin (github.com/Rosentic/cursor-plugin, mcp.json {"command":"rosentic-mcp"}) and the docs' .mcp.json snippets launch. No OpenAPI is published for either surface, so no tool crosswalk is derived.
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.