Vertica Mcp

Created By
hechtcarmela year ago
Allows to query and inspect Vertica databases
Overview

What is Vertica MCP?

Vertica MCP is a Model Context Protocol server designed for readonly communication with Vertica databases, allowing AI assistants to interact with the database safely through a set of readonly operations.

How to use Vertica MCP?

To use Vertica MCP, configure your environment with the necessary Vertica database connection details and set up the MCP server in your application settings. You can run queries directly or through supported AI assistants like Cursor and Claude.

Key features of Vertica MCP?

  • 🔒 Readonly Operations Only: Ensures database safety with SELECT, SHOW, DESCRIBE, EXPLAIN, and WITH queries only.
  • 🏗️ Comprehensive Schema Discovery: List tables, views, and indexes with detailed metadata.
  • 📊 Query Execution: Execute custom SQL queries with parameter support.
  • 🌊 Streaming Support: Efficiently handle large result sets with batch streaming.
  • High Performance: Optimized connection handling and query execution for Vertica.

Use cases of Vertica MCP?

  1. Safely querying Vertica databases without modifying data.
  2. Integrating with AI assistants for data retrieval and analysis.
  3. Performing detailed schema analysis and metadata discovery.

FAQ from Vertica MCP?

  • Can Vertica MCP modify data in the database?

No, Vertica MCP only allows readonly operations to ensure database safety.

  • What are the prerequisites for using Vertica MCP?

You need Node.js 18.x or higher and access to a Vertica database with the appropriate connection details.

  • How do I troubleshoot connection issues?

Verify your database connectivity, check environment variables, and ensure the database user has the necessary permissions.

Server Config

{
  "mcpServers": {
    "vertica-mcp": {
      "command": "npx",
      "args": [
        "@hechtcarmel/vertica-mcp@1.2.2",
        "--env-file",
        "/path/to/your/vertica.env"
      ]
    }
  }
}
Project Info
Created At
a year ago
Updated At
a year ago
Author Name
hechtcarmel
Star
-
Language
-
License
-

Recommend Servers

View All
Docwand

14 hours ago
//beforeyouship — LLM Cost Modeling From Your Editor
@Indiegoing

Query realistic LLM cost models without leaving your editor. beforeyouship models the **true monthly cost** of an LLM app architecture — retries, prompt caching, batch discounts, infra overhead, and 3×/10× growth — across GPT-5.x, Claude, Gemini, DeepSeek, and more. Not a token calculator: a planning tool for the design phase, before you commit to a stack. **No API key needed to try it** — demo mode covers the six free-tier models. A Pro key from [beforeyouship.dev](https://beforeyouship.dev) unlocks the full 18-model catalog. ## What you can ask - "How much will a RAG chatbot cost at 10,000 requests/day?" - "Compare Claude Haiku vs Gemini Flash pricing for my workload" - "What's the cheapest model for a multi-step agent at scale?" - "Show me current per-token prices for Anthropic models" ## Tools ### `estimate_cost` Full cost model for an architecture at a given usage level. Returns Naive / Realistic / Worst Case monthly cost per model, 3×/10× growth scenarios, and an opinionated recommendation with reasoning. ### `get_model_prices` Current per-1M-token pricing — input, output, cached input, batch — with context windows and staleness metadata. ### `list_archetypes` Seven preset architecture patterns (simple chatbot, chatbot with history, RAG pipeline, multi-model router, coding assistant, document processor, multi-step agent) used as starting points for estimates. ## Setup **Claude Code:** ​```bash claude mcp add --transport http beforeyouship https://beforeyouship.dev/api/mcp ​``` **Cursor / other clients** — add a remote server: ​```json { "mcpServers": { "beforeyouship": { "type": "streamable-http", "url": "https://beforeyouship.dev/api/mcp" } } } ​``` Add an `Authorization: Bearer bys_...` header with a Pro key for the full catalog. ## Try it > Estimate the monthly cost of a RAG pipeline at 10,000 requests/day

14 hours ago