llmx/docs/advanced.md

Advanced

If you already lean on LLMX every day and just need a little more control, this page collects the knobs you are most likely to reach for: tweak defaults in Config, add extra tools through Model Context Protocol support, and script full runs with llmx exec. Jump to the section you need and keep building.

Config quickstart

Most day-to-day tuning lives in config.toml: set approval + sandbox presets, pin model defaults, and add MCP server launchers. The Config guide walks through every option and provides copy-paste examples for common setups.

Tracing / verbose logging

Because LLMX is written in Rust, it honors the RUST_LOG environment variable to configure its logging behavior.

The TUI defaults to RUST_LOG=codex_core=info,codex_tui=info,codex_rmcp_client=info and log messages are written to ~/.llmx/log/llmx-tui.log, so you can leave the following running in a separate terminal to monitor log messages as they are written:

tail -F ~/.llmx/log/llmx-tui.log

By comparison, the non-interactive mode (llmx exec) defaults to RUST_LOG=error, but messages are printed inline, so there is no need to monitor a separate file.

See the Rust documentation on RUST_LOG for more information on the configuration options.

Model Context Protocol (MCP)

The LLMX CLI and IDE extension is a MCP client which means that it can be configured to connect to MCP servers. For more information, refer to the config docs.

Using LLMX as an MCP Server

The LLMX CLI can also be run as an MCP server via llmx mcp-server. For example, you can use llmx mcp-server to make LLMX available as a tool inside of a multi-agent framework like the OpenAI Agents SDK. Use llmx mcp separately to add/list/get/remove MCP server launchers in your configuration.

LLMX MCP Server Quickstart

You can launch a LLMX MCP server with the Model Context Protocol Inspector:

npx @modelcontextprotocol/inspector llmx mcp-server

Send a tools/list request and you will see that there are two tools available:

llmx - Run a LLMX session. Accepts configuration parameters matching the LLMX Config struct. The llmx tool takes the following properties:

Property	Type	Description
prompt (required)	string	The initial user prompt to start the LLMX conversation.
approval-policy	string	Approval policy for shell commands generated by the model: untrusted, on-failure, on-request, never.
base-instructions	string	The set of instructions to use instead of the default ones.
config	object	Individual config settings that will override what is in $CODEX_HOME/config.toml.
cwd	string	Working directory for the session. If relative, resolved against the server process's current directory.
model	string	Optional override for the model name (e.g. o3, o4-mini).
profile	string	Configuration profile from config.toml to specify default options.
sandbox	string	Sandbox mode: read-only, workspace-write, or danger-full-access.

llmx-reply - Continue a LLMX session by providing the conversation id and prompt. The llmx-reply tool takes the following properties:

Property	Type	Description
prompt (required)	string	The next user prompt to continue the LLMX conversation.
conversationId (required)	string	The id of the conversation to continue.

Trying it Out

Tip

LLMX often takes a few minutes to run. To accommodate this, adjust the MCP inspector's Request and Total timeouts to 600000ms (10 minutes) under ⛭ Configuration.

Use the MCP inspector and llmx mcp-server to build a simple tic-tac-toe game with the following settings:

approval-policy: never

prompt: Implement a simple tic-tac-toe game with HTML, JavaScript, and CSS. Write the game in a single file called index.html.

sandbox: workspace-write

Click "Run Tool" and you should see a list of events emitted from the LLMX MCP server as it builds the game.