LLM Preflight MCP Server

Last reviewed: 2026-09-30 · As of: v2.19.0 The pre-merge check for LLM changes. Catch model, prompt, schema, and provider-route regressions against your application's contract, then review latency, usage, and price evidence. It runs locally over stdio via the published package.

People who work with benchmark, gemini and model migration and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-09-30 · ★ 2 · #153 OF 998 MAINTAINED OTHER · VERIFIED 2026-09-30

MIT · Python servers · how we verify → /methodology

01 · Install LLM Preflight

before you install - you'll need

The README does not document required environment variables for a basic install.

Claude Code

claude mcp add feronovak-llm-preflight -- uvx llm-preflight

Claude Desktop / Cursor / VS Code - add to config

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

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license MIT - declared in the repository

pypi package llm-preflight - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.feronovak is GitHub-verified and matches the repo owner

03 · What LLM Preflight can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

Limitations (from the README)

[!WARNING] Live benchmarks make paid API requests. Start with the no-key demo, preview the plan before a live run, and keep limits and repetitions small.

Latest releases

v2.19.0 · 2026-09-30

Added · Add native Z.ai GLM-5.3 chat with reviewed input/cache/output pricing, · deterministic streaming and invalid-reasoning fixtures, source detection, · OpenRouter discovery, and a bounded eight-case comparison…

v2.18.2 · 2026-09-28

Fixed · Bundle Claude Sonnet 5.5 ($2 input / $10 output per million tokens) and Claude Haiku 4.5 ($1 / $5) direct-provider prices so new configurations pass strict pricing checks and produce cost estimates. · Omit…

v2.18.1 · 2026-09-28

Fixed · Preserve official native adapter and text-readiness evidence when OpenRouter enriches a provider catalogue entry. · Forward configured system prompts to OpenAI Responses requests so contract checks use the…

04 · Who maintains LLM Preflight

LLM Preflight is maintained by feronovak. It's the only MCP server we track from this author; the repo dates to Jul 2026.

05 · Facts

category
other - ranked #153 of 998 actively-maintained other servers as of 2026-09-30.
release cadence
10+ releases in the last 90 days (latest 2026-09-30)
registry
io.github.feronovak/llm-preflight (active, first published 2026-08-31 · 6 versions)
packages
pypi:llm-preflight

06 · LLM Preflight FAQ

What is LLM Preflight?

Last reviewed: 2026-09-30 · As of: v2.19.0 The pre-merge check for LLM changes. Catch model, prompt, schema, and provider-route regressions against your application's contract, then review latency, usage, and price evidence. It runs locally over stdio via the published package.

Is LLM Preflight still maintained?

Yes - as of 2026-09-30, its last commit was 2026-09-30 and it shipped 10+ releases in the last 90 days. We re-verify nightly.

How do I install LLM Preflight?

Run `uvx llm-preflight`. The README does not document required environment variables for a basic install. You can also paste the ready-made client config above.

Does LLM Preflight run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to LLM Preflight

More MCP servers to compare · Filekiwi MCP Server · Blank Files MCP · fipeX MCP · Dyslex Ia

More Python MCP servers · Gflow CLI · Figma MCP Server (figma) · Python MCP · Vaultbeat Apple Health · FinStack MCP · see all