Loading the directory
Persistent, interactive MCP Apps — the AI builds an app once, you both reuse it
{
"mcpServers": {
"2nd1st-open-mcp-apps": {
"command": "npx",
"args": [
"-y",
"@2nd1st/open-mcp-apps@0.5.9"
],
"env": {
"OMA_DB": "",
"OMA_VIEWER": "",
"OMA_DYNAMIC_TOOLS": ""
}
}
}
}| Name | Required | Notes |
|---|---|---|
| OMA_DB | No | Path to the SQLite store. Defaults to a fixed per-user data directory; set this to isolate a store. |
| OMA_VIEWER | No | Browser viewer on loopback. On by default; set to 0 to turn it off. |
| OMA_DYNAMIC_TOOLS | No | Set to 1 to also expose one open_<name> tool per saved app. Off by default, because it costs prompt cache. |
Tools show up when the registry metadata or the repository README lists them. GitHub enrichment fills this in when a token is configured.
Persistent, interactive MCP Apps — the AI builds an app once, you both reuse it
0 published · no average
Sign in to review this server.
MCP server for Firecrawl — web search, scraping, and biomedical/arXiv paper search.
Google PageSpeed Insights and CrUX: six workflow tools for web performance.
Evidence-backed crypto due diligence with sources, freshness, and a runtime receipt on every call.
Headless Screaming Frog SEO Spider via its CLI: run crawls, export and filter data, no GUI needed.