Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LAD_ENV_FILENoOptional env file path
DEEPSEEK_API_KEYNoOptional API key for DeepSeek
KIMI_CODE_API_KEYNoOptional API key for Kimi Code
OPENROUTER_API_KEYYesAPI key for OpenRouter
OPENROUTER_X_TITLENoOptional X-Title forwarded to OpenRouter
ZAI_CODING_PLAN_KEYNoOptional API key for Z.AI Coding Plan
OPENROUTER_HTTP_REFERERNoOptional HTTP referer forwarded to OpenRouter
INTERMITTENT_REVIEW_CALLSNoNumber of intermittent review calls2
LAD_SERENA_MAX_TOOL_CALLSNoMaximum Serena tool calls32
LAD_SERENA_MAX_DIR_ENTRIESNoMaximum directory entries100
LAD_SERENA_MAX_TOTAL_CHARSNoMaximum total characters50000
OPENROUTER_MAX_INPUT_CHARSNoMaximum input characters100000
OPENROUTER_INCLUDE_REASONINGNoWhether to include reasoning in outputfalse
LAD_SERENA_MAX_SEARCH_RESULTSNoMaximum search results20
OPENROUTER_FIXED_OUTPUT_TOKENSNoFixed output tokens for OpenRouter8192
LAD_SERENA_TOOL_TIMEOUT_SECONDSNoTimeout for Serena tool calls30
LAD_SERENA_MAX_TOOL_RESULT_CHARSNoMaximum tool result characters12000
OPENROUTER_PRIMARY_REVIEWER_MODELNoPrimary reviewer modelmoonshotai/kimi-k2.5
OPENROUTER_CONTEXT_OVERHEAD_TOKENSNoContext overhead tokens for OpenRouter2000
OPENROUTER_MAX_CONCURRENT_REQUESTSNoMaximum concurrent requests to OpenRouter4
OPENROUTER_REVIEWER_TIMEOUT_SECONDSNoWall-clock timeout per reviewer run300
OPENROUTER_SECONDARY_REVIEWER_MODELNoSecondary reviewer model, set to 0 to disableminimax/minimax-m2.7
OPENROUTER_TOOL_CALL_TIMEOUT_SECONDSNoTimeout per tool call360
OPENROUTER_MODEL_METADATA_TTL_SECONDSNoTTL for model metadata caching3600

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
system_design_reviewA

Review a system design proposal and constraints using two LLM reviewers in parallel.

At least one of proposal or paths must be provided.

code_reviewA

Review a code snippet or diff using two LLM reviewers in parallel.

At least one of code or paths must be provided.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Shelpuk-AI-Technology-Consulting/lad_mcp_server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server