Llm Cli Gateway MCP Server

Secure local control plane for AI coding agents across supported MCP clients, with workspace-scoped remote access, approval gates, durable jobs

Remote serverstreamable-httpTypeScript

What is the Llm Cli Gateway MCP Server?

Secure local control plane for AI coding agents across supported MCP clients, with workspace-scoped remote access, approval gates, durable jobs, sessions, and audit

What you get

llm-cli-gateway lets supported MCP clients operate Claude Code, Codex, Gemini/Antigravity, Grok Build, Mistral Vibe, Cognition Devin, Cursor Agent, and configured HTTP API providers through one user-owned gateway while preserving native CLI sessions, local credentials, durable async jobs, validation receipts, and review workflows.

Recorded tools

  • claude — yes
  • gemini — yes
  • grok — yes
  • mistral — yes
  • devin — no

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

Recorded tools

Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.

ToolWhat it does
validate_with_modelsask two or more providers to independently validate a question.
review_changescapture one complete Git review artifact, fence repository
second_opinionask one provider to review an answer.
red_team_reviewchallenge a plan, answer, or document for risks and failure modes.
consensus_checkcheck whether providers agree with a claim.
ask_modelask one provider through the simplified surface.
synthesize_validationrun an explicit judge model after provider results have
list_available_modelslist the models each provider CLI exposes through the simplified surface.
validation_receiptretrieve the canonically hashed immutable receipt of a terminal cross-LLM validation run by validationId (returns minted | pending | verification_failed | expir
Reissuing a request is safe. Identical _request / _request_async calls within the dedup window (default 1 hour) short-circuit onto the existing running or complet
claude_request
codex_request
codex_fork_session
gemini_request
grok_request

How to install the Llm Cli Gateway MCP Server

{
  "mcpServers": {
    "llm-gateway": {
      "command": "npx",
      "args": [
        "-y",
        "llm-cli-gateway"
      ]
    }
  }
}

From the project documentation. Replace placeholders and example paths before connecting.

Example prompts to try

  • “Use Llm Cli Gateway to Machine.”
  • “Use Llm Cli Gateway to Cross.”
  • “Use Llm Cli Gateway to Multi.”

Frequently asked questions

Secure local control plane for AI coding agents across supported MCP clients, with workspace-scoped remote access, approval gates, durable jobs, sessions, and audit Confirm the tools offered by your installed version in the connected client. Tool availability and permissions depend on the server and account configuration.