LLM CLI Gateway — Claude Code MCP server to drive local AI CLIs from one endpoint
A single MCP server that lets Claude Code, Codex, Cursor and other clients run local AI coding agents. Long jobs survive disconnects and are collected later.
claude mcp add llm-cli-gateway -- npx -y llm-cli-gatewayWhat LLM CLI Gateway does
LLM CLI Gateway is a single-user control plane for AI coding agents. From the MCP client you already work in, you can operate Claude Code, Codex, Gemini/Antigravity, Grok Build, Mistral Vibe, Cognition Devin, Cursor Agent and configured HTTP API providers. Native CLI sessions stay intact, local credentials remain local.
Long-running work is kept as durable async jobs: results can be picked up after a restart, with deduplication, cancellation and sync-to-async deferral built in. Remote web connectors use MCP OAuth discovery; client secrets are generated locally, stored as hashes and printed only through explicit copy-once commands. Risky actions pass through approval gates, and review evidence is auditable.
Install globally with npm install -g llm-cli-gateway, then register it in Claude Code with claude mcp add llm-cli-gateway -- npx -y llm-cli-gateway. Grok, Devin and Mistral demand an explicit provider-native sessionId for gateway worktrees: requests without it fail closed.
What it helps with
- run Claude Code, Codex or Gemini from the client you are already in
- collect results from a long job after the connection drops
- scope remote execution to registered workspaces only
- keep auditable evidence for multi-LLM review loops
- gate risky provider actions behind approval
Example prompts for the agent
- Run Claude Code through the gateway and return the result asynchronously
- List registered workspaces and their aliases
- Cancel job
job-123and verify cleanup is scheduled
How to install LLM CLI Gateway
Platform CLI
claude mcp add llm-cli-gateway -- npx -y llm-cli-gatewayPlatform CLI
codex mcp add llm-cli-gateway -- npx -y llm-cli-gatewayConfig file
{
"mcpServers": {
"llm-cli-gateway": {
"command": "npx",
"args": [
"-y",
"llm-cli-gateway"
]
}
}
}Config file
{
"servers": {
"llm-cli-gateway": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"llm-cli-gateway"
]
}
}
}Platform CLI
gemini mcp add llm-cli-gateway npx -y llm-cli-gatewayStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about LLM CLI Gateway
How do I install LLM CLI Gateway in Claude Code?
Run npm install -g llm-cli-gateway, then claude mcp add llm-cli-gateway -- npx -y llm-cli-gateway. The server appears in Claude Code's MCP list.
What does LLM CLI Gateway do?
It lets one MCP client drive several local AI coding agents: Claude Code, Codex, Gemini, Grok Build, Mistral Vibe, Devin, Cursor Agent and configured HTTP providers. Requests flow through the gateway without turning agents into a chat proxy.
Why do Grok, Devin and Mistral requests need a sessionId?
Gateway worktrees for these providers require an explicit provider-native sessionId. Requests with only createNewSession or resumeLatest fail closed because the session cannot be durably reselected.
