mcp-hybrid-data-engine
Supports DuckDB as a columnar analytics backend for Flow plane data queries and aggregations.
Supports Milvus as a vector database backend for Light plane semantic search.
Supports OpenAI as an embedding provider for Light plane semantic indexing.
Enables read-only SQL queries against SQLite databases in the Stone legacy data plane.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-hybrid-data-engineSemantic search for 'customer churn' and show top 3 results with scores"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@vibeleading/mcp-hybrid-data-engine
The Memory Hub.
An MCP server implementing the Vibe Leading Hybrid Data Engine — the integration of the three data planes described in Vibe Leading The AI:
Plane | Role | This server | Production backend |
Stone | Legacy SQL / Oracle, fact ledger |
| Oracle / Postgres + CDC |
Light | Vector semantic context |
| Pinecone / Milvus + embeddings |
Flow | Analytical columnar for the HUD (milliseconds) |
| DuckDB / Parquet |
Installation
npm install -g @vibeleading/mcp-hybrid-data-engine
# or run directly without installing:
npx -y @vibeleading/mcp-hybrid-data-engine
# or run straight from the GitHub source (builds automatically):
npx -y github:VibeLeading/mcp-hybrid-data-engineRelated MCP server: MCP RAG Server
Requirements
Node.js >= 22 — required. The Stone relies on the built-in
node:sqlitemodule, which does not exist in older Node versions. If the server cannot start (missing build or old Node), MCP clients report a generic "connection closed" error.No other runtime dependencies — everything ships with the package.
Quick Start (Agent Setup)
Give your agent the full VibeLeading methodology in one paste:
Give me the Vibe Leading methodology: install the 5 agent skills so I can lead AI agents by intent + real-time telemetry, and add the 4 MCP servers so I get hands in the corporate engine.
SKILLS (npx skills add):
npx skills add VibeLeading/mission-script VibeLeading/ira-prompting VibeLeading/hud-setup VibeLeading/pit-stop-audit VibeLeading/org-geometryMCP SERVERS (@vibeleading scope, add to YOUR agent's MCP config):
@vibeleading/mcp-hybrid-data-engine@vibeleading/mcp-document-architect@vibeleading/mcp-real-time-scout@vibeleading/mcp-privacy-shieldENV VARS:
MCP_STONE_PATH=data/stone.dbMCP_LIGHT_PATH=data/light.jsonMCP_FLOW_PATH=data/flow.jsonMCP_DOCS_ROOT=~/.vlb-docsMCP_SHIELD_NAMES=1NOTE: MCP installation method varies by agent. Examples:
OpenCode:
opencode mcp add hybrid-data-engine -- npx -y @vibeleading/mcp-hybrid-data-engineClaude Code / Cursor: add to
.mcp.json/claude_desktop_config.jsonwithcommand=npx, args=[-y, @vibeleading/mcp-hybrid-data-engine]Codex: configure via its MCP settings UI Use the method appropriate for your agent.
Paste the block above into your AI agent (OpenCode, Claude Code, Cursor, Codex, etc.). It will install the skills, write the MCP config, and you're ready to lead.
Client configuration
Add to your MCP client config (e.g. Claude Code .mcp.json or Cursor mcp.json):
{
"mcpServers": {
"hybrid-data-engine": {
"command": "npx",
"args": ["-y", "@vibeleading/mcp-hybrid-data-engine"]
}
}
}Tools
Tool | Description | Key args |
| Read-only SQL against a SQLite file (Stone) |
|
| CDC version + changed-tables heuristic | — |
| Add a doc to the semantic index (Light) |
|
| Ranked cosine-similarity matches |
|
| Store columnar rows for analytics (Flow) |
|
| sum/avg/min/max/count with optional grouping |
|
Environment variables
Variable | Default | Purpose |
|
| SQLite file used by The Stone |
|
| Persistence file for The Light index |
|
| Persistence file for The Flow store |
Notes
Stone: read-only by design. Statement prefixes are validated; anything outside SELECT/PRAGMA/WITH/EXPLAIN is rejected. The
stone_cdc_tickreports a coarse WAL-based heuristic — a production deployment should wire a real CDC adapter (Debezium + Oracle) behind the same surface.Light: uses a deterministic bag-of-character-ngrams hashed-vector embedding with cosine similarity. Swap in a real embedding provider (OpenAI / voyage) and a real vector DB (Pinecone / Milvus) behind the
Embedderinterface insrc/vector-store.ts.Flow: an in-memory columnar store persisted to JSON. See
src/analytics-engine.tsfor the interface that a DuckDB / Parquet backend would implement.
Publishing
Published to the npm registry via OIDC trusted publishing — no npm tokens stored
anywhere. Pushing a version tag triggers the .github/workflows/publish.yml workflow:
npm version patch -m "release: v%s"
git push origin main --follow-tagsOne-time bootstrap. The very first published version cannot use trusted publishing (the trust relationship attaches to an existing package). Publish
0.1.1once manually (npm publishafternpm login, or a short-lived publish-scoped token), then configure Trusted Publisher on npmjs.com → the package → Settings → Trusted publishing → GitHub Actions → ownerVibeLeading, repomcp-hybrid-data-engine, workflowpublish.yml, actionallow npm publish(requires 2FA once per package).Requires Node.js >= 22 and npm >= 11.5.1 on the runner (handled by the workflow).
License & Attribution
MIT — Copyright (c) 2026 Jean Machuca (see LICENSE).
This server implements concepts from the book Vibe Leading The AI: The Corporate Race Against Machines by Jean Machuca (ISBN 9798252505008, © 2026 Jean Machuca). The book is copyrighted commercial material; this repository does not republish its text. Buy the book at https://vibeleading.org or https://a.co/d/04L5YatK. Author website: jeanmachuca.com · Support on GitHub Sponsors: github.com/sponsors/jeanmachuca. See NOTICE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Query your org's data in natural language — read-only MCP access to SQL, NoSQL, files & warehouses.
Analytical memory for AI agents: a real Postgres queried in plain English over MCP. One command.
Let AI agents query data and act across all your business apps via MCP.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables autonomous orchestration of vector search, knowledge graph queries, and web crawling through a single MCP interface, providing agentic RAG capabilities for AI assistants.7MIT
- AlicenseNot gradedqualityCmaintenanceEnables document ingestion, semantic search, and retrieval-augmented generation via MCP tools and REST API, using vector embeddings and intelligent chunking.MIT

Atlas MCPofficial
AlicenseNot gradedqualityAmaintenanceEnables natural language querying of SQL databases and REST APIs through the MCP protocol, grounded in a semantic layer.2,8871AGPL 3.0- AlicenseNot gradedqualityBmaintenanceEnables enterprise AI agents to query governed data lineage, PII-aware schema documentation, and semantic metadata from SQL logs via MCP, with role-based access and vector search.MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/VibeLeading/mcp-hybrid-data-engine'
If you have feedback or need assistance with the MCP directory API, please join our Discord server