Skip to main content
Glama
lukaisluka

codereview-mcp

by lukaisluka

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MCP_HOSTNoBind address for the MCP endpoint.0.0.0.0
MCP_PORTNoPort for the MCP endpoint.8000
GITHUB_URLNoGitHub or GHE root URL.github.com
GITLAB_URLNoGitLab root URL.
MODEL_NAMENoModel name; a litellm-style provider/ prefix is stripped automatically.openai/deepseek-chat
GITHUB_TOKENNoGitHub token; optional for public repos, required for writes/GHE.
GIT_PROVIDERNoStartup hint; actual routing follows the pr_url shape.gitlab
MCP_ENDPOINTNoMCP endpoint path./mcp
CHUNK_SIZE_KBNoSize threshold for splitting oversized diffs.24
LLM_TIMEOUT_SNoPer-call LLM timeout; keep at or above 180.240
MAX_LLM_CHUNKSNoMaximum number of LLM chunks in map-reduce review.10
MCP_AUTH_TOKENNoOptional server-side bearer check; /health is exempt.
OPENAI_API_KEYNoAPI key for the OpenAI-compatible endpoint; may be empty for intranet hosts.
LLM_CONCURRENCYNoNumber of parallel chunk reviews in map-reduce mode.4
OPENAI_API_BASENoAny OpenAI-compatible endpoint.
REVIEW_LANGUAGENoLanguage for report prose (summary and descriptions).中文
MAX_DIFF_SIZE_KBNoMaximum diff size to review before filtering/splitting.100
NGINX_AUTH_TOKENNoStatic bearer token enforced by the Nginx gateway in Docker compose deployments.
GITLAB_PERSONAL_ACCESS_TOKENNoGitLab personal access token with API scope.

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

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources