# LLM Preflight

> LLM Preflight is an MCP server for ai models and llm tooling. Check LLM outputs against your own rules before swapping a model, prompt or provider. It runs locally on your machine and is started by your AI client.

- **Kind:** MCP server
- **Platforms:** CLI
- **Repository:** https://github.com/feronovak/llm-preflight
- **MCP Registry name:** io.github.feronovak/llm-preflight
- **Categories:** [AI models and LLM tooling](https://ai-powered.com/categories/ai-and-llm), [developer tools](https://ai-powered.com/categories/developer-tools)
- **Listing updated:** 2026-11-15

## About

The core idea is a contract: you describe the JSON shape, routing labels or exact text a feature depends on, then test responses against it. A config can include a response that must pass and a negative control that must fail, so the validator itself gets checked. Exit codes carry the decision: 0 for pass, 1 for fail, 2 for an invalid config and 3 for inconclusive.

Two extras go beyond validation. A source audit scans a repository for literal model IDs that are retired or retiring across Anthropic, OpenAI and selected Gemini models, and suggests a replacement. Dry runs preview provider requests with estimated cost before any call is made. A local mock provider lets you try everything without keys, though a mock run is always inconclusive.

The README is careful about claims: a passing run is evidence for your account, prompts and validators, not production approval. It publishes an observed comparison where 26 model routes ran eight support-routing cases each, with 200 of 208 checks passing. It runs as a CLI, GitHub Action or stdio MCP server and needs Python 3.10 or later, with no third-party runtime dependencies.

## Features

- **Output contracts:** Define allowed labels, JSON shape or exact output and check replies against them.
- **Negative controls:** Fixtures that must fail prove the validator catches bad replies.
- **Retired model audit:** Scans source for model IDs that are retired or retiring and names replacements.
- **Dry-run cost preview:** Shows provider requests and estimated cost before spending anything.
- **CI exit codes:** Distinct codes for pass, fail, invalid config and inconclusive.
- **Local mock provider:** Try the workflow offline without keys or provider calls.

## Good for

- Gate a model upgrade in CI
- Find hard-coded retired model IDs in a repo
- Verify a support-routing prompt only returns allowed labels
- Compare cost and latency of several providers on one contract
- Keep evidence for a prompt change review

## Install

### Claude Code (Terminal)

```sh
claude mcp add llm-preflight -- uvx llm-preflight
```

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "llm-preflight": {
      "command": "uvx",
      "args": [
        "llm-preflight"
      ]
    }
  }
}
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "llm-preflight": {
      "command": "uvx",
      "args": [
        "llm-preflight"
      ]
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "llm-preflight": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "llm-preflight"
      ]
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "llm-preflight": {
      "command": "uvx",
      "args": [
        "llm-preflight"
      ]
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "llm-preflight": {
      "command": "uvx",
      "args": [
        "llm-preflight"
      ]
    }
  }
}
```

## FAQ

### Do I need an API key to try it?

No. The quick start and the source audit work without a key; live checks need provider credentials.

### Does a pass mean it is safe for production?

No. The README says a passing run is evidence for your account, prompts and validators, not production approval.

### Which providers does the model audit cover?

Anthropic, OpenAI and selected Gemini models.

### What does it need to run?

Python 3.10 or later; the README says there are no third-party runtime dependencies.

### How can I use it?

As a CLI, a GitHub Action or a local MCP server.

### How do I add LLM Preflight to Claude Code?

Run this command in your terminal: claude mcp add llm-preflight -- uvx llm-preflight

### What are the best alternatives to LLM Preflight?

The closest alternatives to LLM Preflight are DecisionLint: Jev/Luna Lint, Promptster, GroundLens, LLM Prover and LLM Assure.

## Where this comes from

- Description: written from the project's README.
- Install steps: from the official MCP Registry entry.

## Alternatives

- [DecisionLint: Jev/Luna Lint](https://ai-powered.com/mcp/decisionlint-jev-luna-lint): DecisionLint: Jev/Luna Lint is an open-source MCP server for developer tools.
- [Promptster](https://ai-powered.com/mcp/promptster): Promptster is a freemium MCP server for ai models and llm tooling.
- [GroundLens](https://ai-powered.com/mcp/groundlens): GroundLens is an open-source MCP server for ai models and llm tooling.
- [LLM Prover](https://ai-powered.com/mcp/llm-prover): LLM Prover is a paid MCP server for ai models and llm tooling.
- [LLM Assure](https://ai-powered.com/mcp/llm-assure): LLM Assure is an open-source MCP server for ai models and llm tooling.
- [AIOps Field Notes](https://ai-powered.com/mcp/aiops-field-notes): AIOps Field Notes is an open-source MCP server for knowledge and memory.
- [Localize](https://ai-powered.com/mcp/localize): Localize is an open-source MCP server for ai models and llm tooling.
- [Modelwatch](https://ai-powered.com/mcp/modelwatch): Modelwatch is a freemium MCP server for ai models and llm tooling.

---
Source: https://ai-powered.com/mcp/llm-preflight
