VeriTeknik/pluggedin-app

The Crossroads for AI Data Exchanges. A unified, self-hostable web interface for discovering, configuring, and managing Model Context Protocol (MCP) servers—bringing together AI tools, workspaces, prompts, and logs from multiple MCP sources (Claude, Cursor, etc.) under one roof.

55
/ 100
Established

# Technical Summary Leverages an embedded zvec vector engine (RocksDB + HNSW) for in-process RAG without external dependencies, enabling sub-second semantic search across versioned documents with model attribution tracking. Built on Next.js 15 with PostgreSQL 18 + pgvector, the platform auto-discovers and manages 1,500+ MCP servers via intelligent multi-select filtering while enforcing AES-256-GCM encryption, OAuth 2.1, and sandboxed execution at the document and workspace level. Multi-architecture Docker support (amd64/arm64) enables seamless deployment across heterogeneous infrastructure with persistent vector, database, and log volumes.

No Package No Dependents
Maintenance 13 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

93

Forks

16

Language

TypeScript

License

MIT

Last pushed

Mar 09, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/VeriTeknik/pluggedin-app"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.