Gulliver runs on your own machine — the client starts it, so there is no endpoint to ping. 1 235 installs a week from pypi. Last commit 7 Nov 2026.
Dress rehearsal for agent SQL: cost preflight, auto-fix, 1% sample runs, budget-gated execution.
We read the source, 9 h ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
const r = spawnSync(cmd, ["--version"], { stdio: "ignore" });
proc = subprocess.run([exe, "-C", str(repo), *args], input=stdin, capture_output=True, check=False) # noqa: S603
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add gulliver -- npx -y gulliver-mcp
{
"mcpServers": {
"gulliver": {
"command": "npx",
"args": [
"-y",
"gulliver-mcp"
]
}
}
}
[mcp_servers.gulliver]
command = "npx"
args = ["-y", "gulliver-mcp"]
{
"mcpServers": {
"gulliver": {
"command": "npx",
"args": [
"-y",
"gulliver-mcp"
]
}
}
}
{
"servers": {
"gulliver": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"gulliver-mcp"
]
}
}
}
Governed, read-only Postgres access for AI agents: SQL safety, RLS, budgets, tamper-evident audit.
Deterministic safety, correctness & cost gate that vets Postgres SQL before your AI agent runs it.
Structural preflight for SQLite table-rebuild copy maps.
Read-only, guarded SQL access for AI agents: PostgreSQL, MySQL, ClickHouse, Oracle, SQL Server, Db2
Read PostgreSQL EXPLAIN plans for AI agents: bottlenecks, estimation errors, fixes, charts.
Read-only PostgreSQL for AI agents: every statement is checked before it runs. No account needed.
Safe, audited PostgreSQL operations for AI agents: queries, migrations, EXPLAIN, containers
API-key pre-action risk gate: any irreversible agent action (money, SQL, delete, email).
Answers built from our own checks of this server.