Advertise
MCP.so
Sign In
D

Dbecho MCP Server

@ginkida

Repository

Basic information

Category

Databases

Transports

stdio

Author

ginkida

Submitted by

Sungat Arynov

About Dbecho MCP Server

MCP server for multi-database PostgreSQL analytics. Ask your databases questions in natural language - get schema exploration, profiling, trends, anomaly detection, and cross-database comparisons. Read-only, safe, local.

#postgresql#database#analytics#mcp#python#sql#data-analysis

Dbecho MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "dbecho": {
      "command": "dbecho",
      "args": [
        "--config",
        "/path/to/dbecho.toml"
      ]
    }
  }
}

Dbecho MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Dbecho?

Dbecho gives AI agents (Claude Code, Cursor, Windsurf) direct read-only access to your PostgreSQL databases. It is a pure Python package using stdio transport — no containers or web UI needed.

How to use Dbecho?

Install with pip install, configure your PostgreSQL connection(s) in a TOML file, and Dbecho exposes 11 tools, 3 MCP resources, and 3 MCP prompts to your MCP-compatible AI agent.

Key features of Dbecho

  • 11 tools: schema, query, analyze, compare, trend, anomalies, sample, erd, health, summary, list_databases
  • Read-only safety enforced at the database level
  • Supports multiple PostgreSQL databases in one config
  • Compare databases with a single tool call
  • Pure Python, zero infrastructure required
  • Requires Python 3.10+

Use cases of Dbecho

  • Allow AI coding assistants to explore your database schema and data
  • Query PostgreSQL without granting write or destructive permissions
  • Compare schemas or data patterns across multiple databases
  • Automate database health checks and trend analysis with AI agents
  • Sample and analyze production tables without risk of data modification

Frequently asked questions

1

What safety guarantees does Dbecho provide?

Connections enforce `default_transaction_read_only=on`, only allow SELECT/WITH/EXPLAIN/SHOW queries, prevent SQL injection with `psycopg.sql.Identifier`, and include query timeouts and row limits. It is safe to point at production databases.

2

Do I need to run containers or a web server?

No. Dbecho is a pure Python package that communicates via stdio transport — no containers, web UI, or additional infrastructure required.

3

How do I connect to multiple databases?

Place multiple PostgreSQL connection definitions in a single TOML configuration file. You can compare across them with one tool call.

4

What are the runtime requirements?

Python 3.10 or later is required. There are no other external runtime dependencies.

5

How is Dbecho accessed?

Dbecho uses the standard MCP protocol over stdio transport. It integrates directly with MCP-compatible AI tools such as Claude Code, Cursor, and Windsurf.

Comments

More Databases MCP servers

ClickHouse MCP Server

ClickHouse

Connect ClickHouse to your AI assistants.

818

Elasticsearch MCP Server

elastic

685

MCP DB Wizard

srmadscience

Oracle MCP server with no run-sql tool: It generates tools for each of the PL/SQL procedures, tables and approved SQL you choose. The server doesn't expose a SQL prompt, and can't reveal how it's connected to Oracle.

1

nuzur

nuzur is a model-first database platform for MySQL and PostgreSQL. The MCP server lets any AI assistant or agent (Claude, Cursor, Gemini, or anything else that speaks MCP) design your schema, query your data, generate mi

Local YDB MCP

astandrik

Safety-first stdio MCP server with 38 tools for operating Docker-based local-ydb environments locally or over SSH.

4
Advertise