The request names choosekit-mcp, which does not appear among the candidate products, so no source describes it directly. The closest matches are MCP server frameworks and registries that help select or install MCP tools; the official MCP SDK list and registry marketplaces are the most relevant options shown.
A question back: Did you mean a specific MCP server or registry named choosekit-mcp, and which AI client or language do you need it for?
- 1
Model Context Protocol SDKsmodelcontextprotocol.ioverified and signed
Official SDKs for building MCP servers and clients that expose tools, resources and prompts 3.
official:package · @modelcontextprotocol/sdkrepository · modelcontextprotocolskill · add-app-to-serverskill · convert-web-appskill · migrate-oai-app+17 community tools built for it
for agents: add-app-to-server · mcp-apps · convert-web-app
- 2
McpMuxmcpmux.comwebsite read, tools not yet checked
A registry and marketplace to browse and install 100+ MCP servers, with one local gateway across AI clients 5.
official:MCP server · McpMux
- 3
mpakmpak.devwebsite read, tools not yet checked
An open-source registry for MCP server packages, with security scans and trust scores on every package 6.
- 4
xmcpxmcp.devwebsite read, tools not yet checked
A TypeScript framework for building MCP servers with file-based tools, Zod validation and HTTP or STDIO transports 1.
+3 community tools built for it
Sources
- 1xmcp — The TypeScript MCP frameworkxmcp.dev · read 2026-10-29
- 3SDKs - Model Context Protocolmodelcontextprotocol.io · read 2026-10-29
- 5MCP Server Registry & Marketplace - Browse & Install 100+ MCP Servers | McpMuxmcpmux.com · read 2026-10-29
- 6mpak - Secure MCP Server Registry | Open Source | mpakmpak.dev · read 2026-10-29
For agents: the 10 actions behind this answer
· xmcp website read, tools not yet checked
Build MCP servers in TypeScript with file-based tools, Zod validation, authentication integrations, and HTTP or STDIO transports. Start with xmcp.
· Varity MCP Server Reference website read, tools not yet checked
Install the published Varity MCP package, configure a supported editor, and use its machine-readable tool catalog without relying on unreleased source.
add-app-to-server · add-app-to-server verified and signed
This skill should be used when the user asks to "add an app to my MCP server", "add UI to my MCP server", "add a view to my MCP tool", "enrich MCP tools with UI", "add interactive UI to existing server", "add MCP Apps to my server", or needs to add interactive UI capabilities to an existing MCP serv
get_time_series · Trends MCP found in code, not yet checked
Full historical series for one keyword and one source (0-100
· McpMux website read, tools not yet checked
The largest MCP server registry and marketplace. Browse and install 100+ Model Context Protocol (MCP) servers for Cursor, Claude, VS Code, ChatGPT, Windsurf, JetBrains, and Gemini CLI. Find MCP servers for GitHub, Slack, PostgreSQL, Docker, AWS, Cloudflare, Atlassian, Notion, Stripe, Sentry, and mor
· mpak website read, tools not yet checked
Open-source package registry for MCP servers. Every bundle scanned with 25 security controls. Trust scores on every package.
· Cite42 Docs website read, tools not yet checked
Connect the Cite42 MCP server to Claude, ChatGPT, Codex or Cursor, then ask in plain English for AI search, visibility, keyword and trend data.
· cz-agents website read, tools not yet checked
Open-source MCP servers for AI agents: ARES, ISIR, ÄNB, sanctions, EU business registries. Free tier included. Also available as no-code web DD app for compliance teams.
· Db2i-mcp website read, tools not yet checked
An open-source MCP server that lets Claude, Cursor and other AI assistants read IBM Db2 for i. Read-only by design, with a library allowlist, masking, OAuth sign-in and an audit log.
· state-memory-mcp website read, tools not yet checked
Zero-infrastructure, deterministic Model Context Protocol (MCP) server providing AI coding agents with a structured, persistent SQLite state graph for tracking tasks, decisions, and blockers.
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.