$ llm-cli-gateway.dev --view <TAB>

llm-cli-gateway - one MCP gateway for coding-agent CLIs, local or remote

Claude Code / Codex / Gemini / Grok / Mistral Vibe - durable async jobs - MIT

Paste this into your AI agent:

Read https://llm-cli-gateway.dev/install.md and configure yourself to use llm-cli-gateway as an MCP server.

View the install spec · Repository

or run manually

npx -y llm-cli-gateway

$ npx -y llm-cli-gateway

MCP server connected over stdio

$ LLM_GATEWAY_AUTH_TOKEN=… llm-cli-gateway --transport=http

HTTP MCP server listening on 127.0.0.1:3333/mcp (bearer or OAuth, per-principal isolation)

> consensus_check({ models: ["claude", "codex", "gemini"], claim })

claude_request: accepts with caveat
codex_request: flags missing test
gemini_request: suggests smaller patch
result: disagreement summarized for review

> claude_request_async({ prompt, outputFormat: "stream-json" })

jobId: 1f0c9a2e-…
status: running
persisted: ~/.llm-cli-gateway/logs.db

> llm_job_result({ jobId })

complete - result recovered after gateway restart

API proxy

POST /v1/messages

model response
no native Claude Code session
no Codex CLI resume
no local provider CLI config
file and test access must be rebuilt

Good for hosted chat. Thin for local coding agents.

llm-cli-gateway

MCP tool call

claude_request keeps Claude Code semantics
codex_request uses real Codex sessions
gemini_request uses the installed Antigravity CLI (agy)
grok_request and mistral_request follow provider CLIs

One MCP surface, real local CLIs underneath.

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 MCP endpoint for cross-LLM validation, multi-agent coding workflows, and repeatable assistant-led setup across five provider CLIs.

Local by default over stdio. As of 2.9.0 it also runs remotely over HTTP behind a static bearer token or a built-in OAuth 2.0 server (PKCE on by default, an opt-in human-consent gate, and a trusted-principal-header seam for your own identity proxy), with every session, job, and stored request owned by a principal so one caller never sees another's work, remote calls refused unless a workspace is registered, and a dangerous configuration that fails closed rather than serving open.

Current signals: CI and security workflows pass on main, OpenSSF Scorecard is published, OpenSSF Best Practices is passing, releases use Sigstore signing, and the package is MIT licensed.

claude_request-> Claude Code with sessions and MCP server selection

codex_request-> OpenAI Codex CLI with real resume IDs

*_request_async-> long-running jobs persisted to SQLite

consensus_check-> ask several models and inspect disagreement

session_create-> reusable provider sessions and worktree-aware flows

approval_list-> review approval decisions from one place

The gateway orchestrates local CLIs. It does not replace them.

Posture

CI Security SAST OpenSSF Scorecard OpenSSF Best Practices npm provenance Sigstore CODEOWNERS Dependabot MIT

Signal	Status	Why it matters
Runtime	local stdio or remote HTTP	run on your machine, or expose it behind a bearer token or OAuth
Remote auth	bearer or built-in OAuth 2.0	PKCE, opt-in consent gate, per-principal isolation, fail-closed posture
Async jobs	durable SQLite store	long calls can survive gateway restarts
Validation	cross-model tools	compare, red-team, second opinion, and consensus workflows
Release	npm provenance + Sigstore	published artifacts have supply-chain evidence
License	MIT	open source and installable without a hosted service

Integration

MCP clientsnpx -y llm-cli-gatewaystdio server for Claude Desktop, Claude Code, Codex, Gemini, and other MCP clients (or --transport=http for remote clients)

Provider CLIsclaude / codex / agy / grok / vibeuses the tools and credentials you already installed locally

Registryio.github.verivus-oss/llm-cli-gatewaypublished to the official MCP Registry