Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/stucchi/db-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/stucchi/db-mcp-server/db)<a href="https://agentmods.dev/mcp/stucchi/db-mcp-server/db"><img src="https://agentmods.dev/badge/mcp/stucchi/db-mcp-server/db/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/stucchi/db-mcp-server/db"><img src="https://agentmods.dev/badge/mcp/stucchi/db-mcp-server/db.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
db scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"db": {
"command": "uvx",
"args": [
"db-mcp-server"
],
"env": {
"DB_TYPE": "",
"DB_DATABASE": "",
"DB_MODE": "read-only",
"DB_HOST": "localhost",
"DB_PORT": "",
"DB_USER": "",
"DB_PASSWORD": "",
"DB_URL": "",
"SSH_HOST": "",
"SSH_PORT": "22",
"SSH_USER": "",
"SSH_KEY": "",
"SSH_PASSWORD": ""
}
}
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 23 lines scan A c953207f6ae3
db is an MCP server published in the GitHub repository stucchi/db-mcp-server (2 stars, last pushed 6mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
mcp-server-db
MCP server exposing Postgres, Redis, Elasticsearch, MySQL, MongoDB, and LDAP as tools, with lazy connection management, retry, circuit breaking, per-connection read-only mode, and optional database drivers. Runs locally from the mcp-server-db npm package.
anydb-mcp
Universal database connector for AI agents (Cursor, Claude, Gemini, Zed, Cline). Zero-config MCP server for PostgreSQL, MySQL, SQLite, MongoDB, and Redis. Runs locally from the anydb-mcp npm package.
mcp-db-connect
MCP server for Oracle, MSSQL, PostgreSQL, MySQL, SQLite, MongoDB, and Qdrant vector search access. Runs locally from the mcp-db-connect npm package. Needs 1 environment variable to run.
db-gateway
145+ tools across 8 databases: MySQL, PostgreSQL, Redshift, MongoDB, Redis, Kafka, and more. Runs locally from the db-gateway npm package. Needs 12 environment variables to run.
db-mcp-server
Database MCP server for MySQL, PostgreSQL, MongoDB, and SQLite with SSH tunneling support. Runs locally from the db-mcp-server Python package.
db-mcp-server
Database MCP server for MySQL, PostgreSQL, MongoDB, and SQLite with SSH tunneling support. Runs locally from the db-mcp-server Python package.