Databasement is a self-hosted web application for scheduling, storing, and restoring backups of several kinds of databases. It is for managing database backups across local storage, S3-compatible storage, SFTP, Samba, and other configured destinations, including databases in private networks. The catalogue instruction and MCP integration connect coding agents to its backup-management workflows.
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/David-Crty/databasementWrote 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/david-crty/databasement/laravel-boost)<a href="https://agentmods.dev/mcp/david-crty/databasement/laravel-boost"><img src="https://agentmods.dev/badge/mcp/david-crty/databasement/laravel-boost/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/david-crty/databasement/laravel-boost"><img src="https://agentmods.dev/badge/mcp/david-crty/databasement/laravel-boost.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
laravel-boost 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 10d 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
{
"laravel-boost": {
"command": "docker",
"args": [
"compose",
"exec",
"--user",
"application",
"-T",
"app",
"php",
"artisan",
"boost:mcp"
]
}
}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.
- 10d ago First seen · 16 lines scan A 08ffe93cf1fc
laravel-boost is an MCP server published in the GitHub repository David-Crty/databasement (2,354 stars, last pushed 2d 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 2026-08-30.
Other mcp servers, from other repositories
mcp-datalink
MCP server for secure database access (PostgreSQL, MySQL, SQLite). Runs locally from the @pilat/mcp-datalink npm package. Needs 2 environment variables to run.
mcp-ssh-manager
SSH server management for agents, with per-server read-only and allowlist security modes. Runs locally from the mcp-ssh-manager npm package. Needs 2 environment variables to run.
xcode
MCP server "xcode" as configured in Sequel-Ace/Sequel-Ace. Launched with xcrun mcpbridge.
bintrail
MCP server "bintrail" as configured in dbtrail/dbtrail. Launched with go run ./cmd/bintrail-mcp. Needs 1 environment variable to run.
dbmcp
MCP server "dbmcp" as configured in haymon-ai/dbmcp. Runs in Docker (ghcr.io/haymon-ai/dbmcp:0.9.1).
dbconvert-streams
Read-only SQL across PostgreSQL, MySQL, S3 buckets and local data files — one query can join across all of them. MCP server. Runs locally from the @dbconvert/stream-mcp npm package. Needs 1 environment variable to run.