mcpbeat Sign in

LLM Preflight MCP Server

by feronovak Your server? Claim it
local only

LLM Preflight runs on your own machine — the client starts it, so there is no endpoint to ping. 1 269 installs a week from pypi. Last commit 7 Nov 2026.

Local, cross-provider preflight checks for LLM integration changes.

Installs per day peak 868 · avg 244 · +24% w/w
a month agotoday
1 269
Installs / week
pypi · llm-preflight
3
Stars
0 open issues
7 Nov 2026
Last commit
from GitHub
MIT
License
Python

What the code does

We read the source, 1 d ago · rules 995398eba69f

Capabilities

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.

    return subprocess.run(  # nosec B603

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

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.

Three servers free · no card

Connect this server

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.

run in your terminal
claude mcp add llm-preflight -- uvx llm-preflight
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "llm-preflight": {
      "command": "uvx",
      "args": [
        "llm-preflight"
      ]
    }
  }
}
~/.codex/config.toml
[mcp_servers.llm-preflight]
command = "uvx"
args = ["llm-preflight"]
.cursor/mcp.json
{
  "mcpServers": {
    "llm-preflight": {
      "command": "uvx",
      "args": [
        "llm-preflight"
      ]
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "llm-preflight": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "llm-preflight"
      ]
    }
  }
}

Alternatives to LLM Preflight

same job, measured the same way
orm-preflight
by sikandar100

Checks TypeORM migrations for data loss, table locks, and deploy problems before they run.

69 installs/wk local only
Chanty
by asklokesh

MCP server for Chanty API integration

129 installs/wk local only
T
Think MCP
by agentutil

Intent security pre-flight checks for autonomous AI agents.

33 installs/wk local only
C
Cortex Test MCP Server
by sasikumarlilly

Internal test MCP server for local dev and Bifrost integration testing.

local only
ResultGate
by ahedmuni

Local service recommendations for six providers, disclosed referrals and evidence checks.

163 installs/wk local only
LLMVerify
by subodhkc

Local-first MCP server for LLM output verification — risk signals, injection and PII checks.

1 342 installs/wk local only
MCP Victorialogs
by victoriametrics-community

MCP Server for VictoriaLogs. Provides integration with VictoriaLogs API and documentation

local only
MCP Victorialogs
by victoriametrics

MCP Server for VictoriaLogs. Provides integration with VictoriaLogs API and documentation

local only

LLM Preflight — questions

Answers built from our own checks of this server.

Why is there no uptime for LLM Preflight?
LLM Preflight runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package llm-preflight was installed 1 269 times last week.
How do I connect LLM Preflight?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls llm-preflight straight from pypi; nothing to host, nothing to sign up for.
How many people use LLM Preflight?
The pypi package llm-preflight was installed 1 269 times in the last week. Week over week that is +24%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is LLM Preflight open source?
Yes — it is published under the MIT licence, written in Python and 3 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.