MCP Tools Directory
← Browse integrations

Developer tools

io.github.Idle-Sync/db-conn-mcp

Free account · sign-in required

Contact io.github.Idle-Sync/db-conn-mcp

Loading secure sign-in…

Tools for autonomous AI agents

About this integration

A dead-simple, self-hosted MCP server for securely querying databases via AI agents.

Transport
stdio
Authentication
unknown
Initial setup
credentials
Runtime
unattended
Evidence
documented
Version
0.7.1
Package
db-conn-mcp
Last compatibility test
Not independently tested

Connect your agent

db-conn-mcp

Publisher README and Python project manifest reviewed; package and databases were not executed. The publisher recommends a database-level read-only role as the strongest boundary; write mode has preview and consent gates.

Capabilities: PostgreSQL schema and data exploration, Read queries, cursors, statistics, and schema comparison, Gated write queries and connection diagnostics

Connected profiles

Additional details

Registry identifier

io.github.Idle-Sync/db-conn-mcp

Source ↗ · Checked 2026-09-17
Published version

0.7.1

Source ↗ · Checked 2026-09-17
Metadata license

CC0-1.0; package licenses are separate

Source ↗ · Checked 2026-09-17
Package ecosystem

pypi

Source ↗ · Checked 2026-09-17
Source artifact

db-conn-mcp

Source ↗ · Checked 2026-09-19
Source manifest version

0.7.1

Source ↗ · Checked 2026-09-19
Unattended configuration

The installed db-conn-mcp command runs a stdio server by default and can alternatively serve HTTP SSE.

Source ↗ · Checked 2026-09-19
Authentication and prerequisites

Database access is configured with a DSN that can contain database-role credentials; this database-native mechanism is outside the catalog's API-key and OAuth taxonomy.

Source ↗ · Checked 2026-09-19
Connection configuration

MCP clients launch db-conn-mcp over stdio and pass the path to connections.json, which names each PostgreSQL DSN and access mode.

Source ↗ · Checked 2026-09-19
Review scope

Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.

Source ↗ · Checked 2026-09-19