ai-cli-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CODEX_CLI_NAME | No | Override the Codex CLI binary name or provide an absolute path | codex |
| FORGE_CLI_NAME | No | Override the Forge CLI binary name or provide an absolute path | forge |
| CLAUDE_CLI_NAME | No | Override the Claude CLI binary name or provide an absolute path | claude |
| GEMINI_CLI_NAME | No | Override the Gemini CLI binary name or provide an absolute path | gemini |
| MCP_CLAUDE_DEBUG | No | Enable debug logging (set to true for verbose output) | false |
| OPENCODE_CLI_NAME | No | Override the OpenCode CLI binary name or provide an absolute path | opencode |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| runA | AI Agent Runner: Starts a Claude, Codex, Antigravity (Gemini), OpenCode, Grok, or Pi CLI process in the background and returns a PID immediately. Use list_processes and get_result to monitor progress. • File ops: Create, read, (fuzzy) edit, move, copy, delete, list files, analyze/ocr images, file content analysis • Code: Generate / analyse / refactor / fix • Git: Stage ▸ commit ▸ push ▸ tag (any workflow) • Terminal: Run any CLI cmd or open URLs • Web search + summarise content on-the-fly • Multi-step workflows & GitHub integration IMPORTANT: This tool now returns immediately with a PID. Use other tools to check status and get results. Supported models: "claude-ultra", "codex-ultra", "gemini-ultra", "sol", "luna", "sonnet", "sonnet[1m]", "opus", "opusplan", "fable", "haiku", "gpt-6-astra", "gpt-6-sol", "gpt-6-luna", "gpt-5.4", "gpt-5.6-sol", "gpt-5.6-terra", "gpt-5.6-luna", "gpt-5.5", "gpt-5.4-mini", "gpt-5.3-codex", "gpt-5.3-codex-spark", "gpt-5.2", "gemini-3.8-flash-high", "gemini-3.8-flash-medium", "gemini-3.8-flash-low", "gemini-3.7-flash-high", "gemini-3.7-flash-medium", "gemini-3.7-flash-low", "gemini-3.6-flash-high", "gemini-3.6-flash-medium", "gemini-3.6-flash-low", "gemini-3.1-pro-high", "gemini-3.1-pro-low", "grok", "grok-4.6", "grok-4.5", "opencode", "pi", "oc-<provider/model>", "pi-<provider/model>" Prompt input: You must provide EITHER prompt (string) OR prompt_file (file path), but not both. Prompt tips
|
| list_processesA | List all running and completed AI agent processes. Returns a simple list with PID, agent type, and status for each process. |
| get_resultA | Get the current output and status of an AI agent process by PID. Defaults to a compact result shape; set verbose to true for full metadata and detailed parsed output. |
| waitB | Wait for multiple AI agent processes to complete and return their results. Defaults to compact result items; set verbose to true for full metadata and detailed parsed output. |
| peekA | One-shot short observation window for running child agents. Returns only natural-language message events, and optionally normalized tool_call events, observed during this call; not a history API, not gapless streaming, and not stdout/stderr tailing. Message extraction is supported for Codex, Claude, Grok (whole assistant messages), OpenCode, Gemini, and Pi text deltas. Tool calls exclude raw tool output. |
| kill_processC | Terminate a running AI agent process by PID. |
| cleanup_processesA | Remove all completed and failed processes from the process list to free up memory. |
| doctorA | Check supported AI CLI binary availability and path resolution, including Grok (GROK_CLI_NAME override) and Pi (PI_CLI_NAME override). Does not verify login state or terms acceptance. |
| modelsA | List supported model names, aliases, and reasoning effort levels. Queries Pi and OpenCode for current models and returns names ready for run. Discovery uses a 5-second timeout per CLI and a 60-second process-local cache; failures are reported per backend without hiding other models. Lists reflect the server working directory and CLI configuration, not a guarantee of model access. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Each tool has a clearly distinct purpose: run starts processes, list/get_result/wait monitor them, kill/cleanup manage them, peek provides live observation, doctor checks CLI availability, and models lists supported models. No two tools overlap in function.
Naming is mixed: some tools follow verb_noun (cleanup_processes, list_processes, get_result, kill_process) while others are bare verbs (run, wait, peek) or nouns (doctor, models). The pattern is not uniform but still readable and intuitive.
With 9 tools, the server is well-scoped for AI CLI process management and model discovery. Each tool covers a necessary aspect of the workflow without redundancy or bloat.
The tool surface covers the full lifecycle: creating processes (run), monitoring (list, get_result, wait, peek), terminating (kill, cleanup), and supporting infrastructure (doctor, models). No obvious gaps for the stated purpose.