Skip to main content
Glama
tsarihan

model-council-mcp-codex

by tsarihan

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
GROK_CLINoSet to 'true' to add subscription-backed Grok members via local grok CLIfalse
CODEX_CLINoSet to 'true' to add subscription-backed ChatGPT member via local codex exec CLIfalse
MAX_FILESNoMax number of attached files32
CLAUDE_CLINoSet to 'true' to add subscription-backed Claude members via the local claude CLIfalse
MAX_TOKENSNoMax output tokens per completion32768
JUDGE_MODELNoJudge model ID or 'auto'auto
MAX_FILE_KBNoPer-file cap in KB512
XAI_API_KEYNoEnables X.AI Grok models
MAX_TOTAL_KBNoTotal across all attached files in KB1536
VLLM_SERVERSNoComma-separated list of name:host:port for vLLM servers
GROK_CLI_PATHNoPath to the grok binarygrok
RESPONSE_MODENoResponse mode: individual, categorized, deconflicted, pooled, dialecticcategorized
CODEX_CLI_PATHNoPath to the codex binarycodex
COUNCIL_MODELSNoComma-separated model IDs
MAX_CONTEXT_KBNoInline context string cap in KB1024
OLLAMA_ADDRESSNoBase URL of your Ollama serverhttp://localhost:11434
OPENAI_API_KEYNoEnables OpenAI models
SGLANG_SERVERSNoComma-separated list of name:host:port for SGLang servers
TRTLLM_SERVERSNoComma-separated list of name:host:port for TRT-LLM servers
CLAUDE_CLI_PATHNoPath to the claude binaryclaude
GROK_CLI_MODELSNoModel names for the Grok CLI membergrok-4.5
MAX_QUESTION_KBNoQuestion string cap in KB256
CODEX_CLI_MODELSNoModel names for the Codex memberdefault
ANTHROPIC_API_KEYNoEnables Anthropic Claude models
CLAUDE_CLI_MODELSNoModel aliases for the Claude CLI memberopus,sonnet
CLOUD_CONCURRENCYNoMax simultaneous requests to cloud members3
LOCAL_CONCURRENCYNoMax simultaneous requests to local models; 0 = unlimited1
COMPLETION_RETRIESNoAttempts per completion before giving up3
DECONFLICT_VERBOSENoIf 'true', deconflicted results include per-round detail by defaultfalse
REQUEST_TIMEOUT_MSNoPer-completion wall-clock timeout in ms for text-only calls300000
MODEL_COUNCIL_STATENoPath to persistent state file (overrides ~/.config/model-council/state.json)
MAX_DECONFLICT_ROUNDSNoMax deconfliction iterations3
REPO_REQUEST_TIMEOUT_MSNoPer-completion timeout in ms when full_repo_access is set600000
CLAUDE_CLI_OLLAMA_MODELSNoComma-separated Ollama model names to run through the claude CLI harness
CLAUDE_CLI_OLLAMA_ADDRESSNoOllama address for the harness member, if different from OLLAMA_ADDRESS
GROK_CLI_UNSAFE_ACCEPT_RCENoSet to 'true' to re-enable Grok CLI members (unsafe, testing only)false

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

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/tsarihan/model-council-mcp-codex'

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