codereview-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| STREAM | No | Stream responses; falls back to a single request if unsupported. | true |
| MAX_TOKENS | No | Max tokens per response. | 4096 |
| TEMPERATURE | No | Sampling temperature (0â2). | 0.3 |
| LLM_PROVIDER | No | The LLM provider to use: ollama, openai, anthropic, or openrouter. | ollama |
| OLLAMA_MODEL | No | Ollama model name. | llama3.2:3b |
| OPENAI_MODEL | No | OpenAI model name. | gpt-4o-mini |
| CUSTOM_PROMPT | No | Override the review prompt (must contain {code} and {language}). | |
| OPENAI_API_KEY | No | OpenAI API key (required for OpenAI provider). | |
| ANTHROPIC_MODEL | No | Anthropic model name. | claude-sonnet-4-6 |
| MAX_INPUT_CHARS | No | Reject inputs larger than this. | 100000 |
| OLLAMA_BASE_URL | No | Ollama server URL. | http://localhost:11434 |
| OPENAI_BASE_URL | No | Custom OpenAI-compatible endpoint. | |
| REQUEST_TIMEOUT | No | Per-request timeout in seconds. | 120 |
| OPENROUTER_MODEL | No | OpenRouter model slug. | qwen/qwen3-coder-30b-a3b-instruct |
| ANTHROPIC_API_KEY | No | Anthropic API key (required for Anthropic provider). | |
| OPENROUTER_API_KEY | No | OpenRouter API key (required for OpenRouter provider). | |
| OPENROUTER_BASE_URL | No | OpenRouter endpoint. | https://openrouter.ai/api/v1 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| review_git_diffA | Review a git diff for bugs, security issues, and improvements. Accepts the output of Example: git diff | review_git_diff |
| review_code_fileB | Review an entire source file for bugs and improvements. Provide the absolute path to a file. Language is auto-detected from the file extension. Supports 50+ languages. Best for: reviewing new files, complete rewrites, or files where you want a comprehensive analysis of the entire codebase. |
| review_code_snippetA | Review a code snippet (not from a file) in the specified language. Use this when you have a small piece of code to review that isn't in a file yet, or when you want to review an isolated snippet. Args: code: The source code to review. language: Programming language (python, javascript, rust, go, etc.) |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool targets a distinct input type: file, snippet, or git diff. The descriptions clearly differentiate them, leaving no ambiguity about when to use each.
All tools follow the consistent 'review_<source>' pattern (review_code_file, review_code_snippet, review_git_diff), making naming predictable and clear.
Three tools is appropriate for the code review domain, covering the main scenarios without being too few or too many.
The surface covers the primary use cases: reviewing files, snippets, and diffs. Potential additions like reviewing a pull request or URL are missing but not essential.