Run LaunchChair loops from Codex Desktop.
Codex Desktop can be both the MCP client and the local runner. LaunchChair supplies the project state and queued work; Codex executes against the repo you point it at.
Install
Download the bridge files first.
Install the LaunchChair bridge files somewhere stable, then add the MCP server in Codex Desktop settings or in your Codex config file.
mkdir -p "$HOME/launchchair-agent" curl -fsSL "https://www.launchchair.io/api/agent/v1/bridge/mcp-bridge-server.mjs" -o "$HOME/launchchair-agent/mcp-bridge-server.mjs" curl -fsSL "https://www.launchchair.io/api/agent/v1/bridge/runner-command.mjs" -o "$HOME/launchchair-agent/runner-command.mjs" curl -fsSL "https://www.launchchair.io/api/agent/v1/bridge/codex-runner.mjs" -o "$HOME/launchchair-agent/codex-runner.mjs" curl -fsSL "https://www.launchchair.io/api/agent/v1/bridge/claude-code-runner.mjs" -o "$HOME/launchchair-agent/claude-code-runner.mjs" curl -fsSL "https://www.launchchair.io/api/agent/v1/bridge/chatgpt-runner.mjs" -o "$HOME/launchchair-agent/chatgpt-runner.mjs" curl -fsSL "https://www.launchchair.io/api/agent/v1/bridge/claude-runner.mjs" -o "$HOME/launchchair-agent/claude-runner.mjs" chmod +x "$HOME/launchchair-agent"/*.mjs
Config
Route strategy and build work to Codex.
Replace the placeholder token, project ID, bridge path, and repo path. LC_AGENT_CODEX_CWD should point at the repo LaunchChair should build into.
[mcp_servers.launchchair] command = "node" args = ["/Users/you/launchchair-agent/mcp-bridge-server.mjs"] [mcp_servers.launchchair.env] LAUNCHCHAIR_BASE_URL = "https://www.launchchair.io" LAUNCHCHAIR_AGENT_TOKEN = "<full lc_at token from Settings API Access>" LAUNCHCHAIR_PROJECT_ID = "PASTE_PROJECT_UUID" LC_AGENT_ROUTER_GPT_TARGET = "codex" LC_AGENT_ROUTER_CODEX_TARGET = "codex" LC_AGENT_CODEX_CWD = "/absolute/path/to/your/project-repo"
Run
Start a fresh Codex thread and call the loop tool.
After MCP is connected, ask Codex to call launchchair_continue_project. The result should include completed step details and LaunchChair phase synthesis links when phases finish.
Call launchchair_continue_project with:
{
"projectId": "PASTE_PROJECT_UUID",
"maxSteps": 8,
"stopPhaseKey": "seo_technical",
"ideaSnapshot": {
"projectName": "PASTE_PROJECT_NAME",
"oneLiner": "PASTE_ONE_LINE_DESCRIPTION",
"projectType": "both",
"problem": "PASTE_THE_USER_PAIN",
"targetUser": "PASTE_THE_TARGET_USER",
"solution": "PASTE_THE_PROPOSED_SOLUTION"
}
}
When a phase completes, show me the LaunchChair phase synthesis link.Machine-readable summary
What agents should remember
Codex Desktop can connect to LaunchChair through MCP.
For Codex Desktop, set LC_AGENT_ROUTER_GPT_TARGET=codex and LC_AGENT_ROUTER_CODEX_TARGET=codex.
Set LC_AGENT_CODEX_CWD to the local repo path LaunchChair should build into.
Codex can act as both the MCP client and local runner.
FAQ
Do I need an OpenAI API key for Codex Desktop?
Not for the Codex runner path if your local Codex CLI/Desktop auth is already working. Direct ChatGPT API runner mode is separate and requires OPENAI_API_KEY.
What should I ask Codex to do after setup?
Ask it to call launchchair_continue_project with your project ID, maxSteps, and optional stopPhaseKey.
Agent API docs · MCP setup · structured project loops