list_processes
Lists all running and completed AI agent processes with their status, PID, and basic info.
How to use it
list_processes is exposed by the Ai Cli MCP MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the list_processes tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
Install Ai Cli MCP
claude mcp add ai-cli '{"name":"ai-cli","command":"npx","args":["-y","ai-cli-mcp@latest"]}'Other tools in Ai Cli MCP (22)
is claude, codex, gemini, forge, opencode, a future tracked string value, or null when the process is not found or the agent cannot be determined.
Checks supported AI CLI binary availability and path resolution from MCP clients. Like ai-cli doctor, it returns a checks block and does not verify login state or terms acceptance.
explicitly selects Claude Code's latest Fable model. Fable may require separately billed usage credits and is never selected implicitly by claude-ultra.
Gets the current output and status of an AI agent process by PID.
(boolean, optional): When true, each process events array includes normalized toolcall events in addition to message events. Defaults to false.
Terminates a running AI agent process by PID.
Lists supported model names, aliases, and dynamic backend discovery hints from MCP clients. This returns the same structured payload as ai-cli models.
Starts a one-shot short observation window for running child agents and returns structured events observed during that specific call. By default this includes only natural-language message events; pass includetoolcalls or --include-tool-calls to also include normalized tool-call events. It is not a
and events[].ts are ai-cli-mcp server-side UTC RFC3339 timestamps. peekstartedat is when the observation window starts after validation and listener registration; events[].ts is when ai-cli-mcp observed and accepted the event.
(number, optional): Positive integer observation length in seconds. Defaults to 10 and is capped at 60. 0, negative values, and fractional values are invalid.
(number, required): The process ID returned by the run tool.
(array of numbers, required): List of process IDs to wait for (returned by the run tool).
(string, optional): The prompt to send to the AI agent. Either prompt or promptfile is required.
(string, optional): Path to a file containing the prompt. Either prompt or promptfile is required. Can be absolute path or relative to workFolder.
(string, optional): Reasoning control for Claude and Codex. Claude uses --effort (allowed: "low", "medium", "high", "xhigh", "max"). Codex uses modelreasoningeffort (base levels: "low", "medium", "high", "xhigh"; GPT-5.6 Sol/Terra also support "max" and "ultra", while Luna supports "max"). Gemini, F
Executes a prompt using Claude CLI, Codex CLI, Gemini CLI, Forge CLI, or OpenCode. The appropriate CLI is automatically selected based on the model name.
(string, optional): Optional session ID to resume a previous session. Supported for Claude, Codex, Gemini, Forge, and OpenCode. OpenCode resumes in place via --session and may also be combined with an explicit oc-<provider/model> selection.
is one of running, completed, failed, or notfound, and reflects state when the observation window closes.
(number, optional): Maximum wait time in seconds. Defaults to 180 (3 minutes).
(boolean, optional): If true, each result item uses the full result shape. Defaults to false.
Waits for multiple AI agent processes to complete and returns their combined results. Blocks until all specified PIDs finish or a timeout occurs.
(string, required): The working directory for the CLI execution. Must be an absolute path.