How do I connect Ai Cli MCP Server to Claude?

The listing records `claude mcp add ai-cli '{"name":"ai-cli","command":"npx","args":["-y","ai-cli-mcp@latest"]}'` as its setup step. Run it, then follow the repository's instructions for the client configuration; the listing names Claude Code, Cursor, Windsurf as compatible clients.

Is Ai Cli MCP Server free?

The listed licence is MIT. Check the upstream terms for permitted use and commercial requirements; a public repository does not by itself mean the software is free or open source. Connected APIs and hosted services may have separate charges.

What can Ai Cli MCP Server do?

Ai Cli MCP Server documents 8 tools to the agent, including doctor, get_result, kill_process. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.

Ai Cli MCP

Unclaimed

by mkXultra

MCP server to run Claude, Codex, and Gemini CLI agents in the background from any MCP client.

Install

$claude mcp add ai-cli '{"name":"ai-cli","command":"npx","args":["-y","ai-cli-mcp@latest"]}'

Set up this server

Compare servers My Stack

This server needs project-specific setup. Follow the project instructions; no reusable public launch command is available yet.

Project instructions

claude-codecodexgemini-climcp-server

Is this your MCP server?

This listing was auto-indexed from the public record. Claim it to edit the page, set compatibility and unlock growth tools. Takes under two minutes.

Claim this server

Security profile

Claimed and verified servers get a weekly static scan that shows what the code can reach: external services, environment variables, shell commands, agent configuration folders, plus any dependencies with known advisories. Claim this listing to get one. How the security profile works

8 of 8 tools

Documented tools (8)

From project documentation. A server handshake does not verify each tool’s description or behavior.

doctor

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.

get_result

Gets the current output and status of an AI agent process by PID.

kill_process

Terminates a running AI agent process by PID.

list_processes

Lists all running and completed AI agent processes with their status, PID, and basic info.

models

Lists supported model names, aliases, and dynamic backend discovery hints from MCP clients. This returns the same structured payload as ai-cli models.

peek

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

run

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.

wait

Waits for multiple AI agent processes to complete and returns their combined results. Blocks until all specified PIDs finish or a timeout occurs.

Tool change history

Compared across complete checks of the same configuration. Tools were listed, not invoked. Input-schema changes are not measured here.

No complete tool checks yet.

FAQ

Questions about Ai Cli MCP Server

How do I connect Ai Cli MCP Server to Claude?: The listing records `claude mcp add ai-cli '{"name":"ai-cli","command":"npx","args":["-y","ai-cli-mcp@latest"]}'` as its setup step. Run it, then follow the repository's instructions for the client configuration; the listing names Claude Code, Cursor, Windsurf as compatible clients.
Is Ai Cli MCP Server free?: The listed licence is MIT. Check the upstream terms for permitted use and commercial requirements; a public repository does not by itself mean the software is free or open source. Connected APIs and hosted services may have separate charges.
What can Ai Cli MCP Server do?: Ai Cli MCP Server documents 8 tools to the agent, including doctor, get_result, kill_process. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.