Question 1

What LLM providers are supported?

Accepted Answer

OpenAI (default gpt‑4o), Anthropic (default claude‑3‑opus‑20240307), and Gemini (default gemini‑1.5‑pro). You can also override the default models for each provider.

Question 2

How do I configure the server?

Accepted Answer

Set your preferred provider via `LLM_PROVIDER` and the corresponding API key in a `.env` file (e.g., `OPENAI_API_KEY`). Optional model overrides are available.

Question 3

What does the code review output look like?

Accepted Answer

A structured JSON object containing a summary, a list of issues (each with type, severity, description, line numbers, and recommendation), a list of strengths, and overall recommendations.

Question 4

What credentials does it need?

Accepted Answer

It reads `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, `GEMINI_API_KEY` from the environment. Store these in your client's env block or a secrets manager — never commit them to a repository — and grant the narrowest scope that still covers your use case.

Tool	What it does
analyze_repo
code_review

Variable	Description	Required
OPENAI_API_KEY	Credential the server authenticates with.	Yes
ANTHROPIC_API_KEY	Credential the server authenticates with.	Yes
GEMINI_API_KEY	Credential the server authenticates with.	Yes

Code Review Server MCP Server

What is the Code Review Server MCP Server?

The short version

More MCP options

Recorded tools

Configuration

Example prompts to try

Frequently asked questions

Alternatives to the Code Review Server MCP Server

Filesystem

Context7

Teamcity

Nodit

Dooray MCP

Flowra