llm-cli-gateway
A Model Context Protocol (MCP) gateway for running Claude Code, Codex, Gemini, Grok, and Mistral (Vibe) CLIs from one MCP endpoint, with durable async jobs, session continuity, cache-aware prompting, observability, and personal-appliance setup tooling. Why developers try it: one local MCP endpoint for cross-LLM validation, multi-agent coding workflows.
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find.
Install from
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
When Vitest UI server is listening, arbitrary file can be read and executed
process.env. You'll be asked to provide them before it can run.APPROVAL_LOG_PROMPTSCLAUDE_DEFAULT_MODELCLAUDE_SETTINGS_LOCAL_PATH— /path/to/settings.local.jsonCLAUDE_SETTINGS_PATH— /path/to/settings.jsonCODEX_CONFIG_PATH— /path/to/config.tomlCODEX_DEFAULT_MODEL— codex-model-id>DATABASE_URLGEMINI_DEFAULT_MODEL— gemini-2.5-flashGEMINI_DISABLE_HISTORY_DISCOVERYGEMINI_HISTORY_MAX_FILESGEMINI_HISTORY_MAX_FILE_BYTESGEMINI_HISTORY_ROOT— /path/to/.gemini/tmpGEMINI_SETTINGS_PATH— /path/to/settings.jsonGROK_DEFAULT_MODELINTEGRATION_TESTSLLM_GATEWAY_ACKNOWLEDGE_EPHEMERAL— 1/true/yes sets acknowledgeEphemeral = true.LLM_GATEWAY_APPROVAL_POLICY— Default approval policy when request does not pass approvalPolicy (strict, balanced, permissive)LLM_GATEWAY_CONFIG— The job-store backend is configured by ~/.llm-cli-gateway/config.toml (override with =/path/to/config.toml). Example:LLM_GATEWAY_DEDUP_WINDOW_MS— overrides dedupWindowMs.LLM_GATEWAY_DISABLE_MODEL_DISCOVERYLLM_GATEWAY_HTTP_HOSTLLM_GATEWAY_HTTP_PATHLLM_GATEWAY_HTTP_PORTLLM_GATEWAY_JOBS_DB— LLM_GATEWAY_LOGS_DB / — none selects backend = "none"; any other value selects backend = "sqlite" with that path.LLM_GATEWAY_JOB_RETENTION_DAYS— overrides retentionDays.LLM_GATEWAY_LOGS_DB— / LLM_GATEWAY_JOBS_DB — none selects backend = "none"; any other value selects backend = "sqlite" with that path.LLM_GATEWAY_MODEL_ALIASES— 'codex.fast=gpt-5.3-codex-spark,gemini.fast=gemini-team-default'LLM_GATEWAY_NO_AUTH_PATHSLLM_GATEWAY_OAUTH_OPEN_DEVLLM_GATEWAY_PUBLIC_URLLLM_GATEWAY_TOOL_DISCOVERY_HOMELLM_GATEWAY_TRANSPORTLLM_GATEWAY_WORKSPACE_ADMINMCP_TRANSPORTMISTRAL_DEFAULT_MODELPG_TESTSSESSION_TTLSYNC_DEADLINE_MSVIBE_ACTIVE_MODEL— Model selection is via the environment variable —VIBE_HOMEVIBE_MODELS— , injects VIBE_ACTIVE_MODEL only when a model is explicitly[](https://m8ven.ai/mcp/verivus-oss-llm-cli-gateway-fqq7et)