AI Cli MCP vs Remote Agents
A side-by-side look at the AI Cli MCP and Remote Agents MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose AI Cli MCP for command line work as a local process; choose Remote Agents for command line as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose AI Cli MCP when
- You need dedicated capabilities in the Command Line domain.
- You prefer a local stdio subprocess transport.
- You want tools like
run, wait, peek.
Choose Remote Agents when
- You need dedicated capabilities in the Command Line domain.
- You prefer a local stdio subprocess transport.
- You want tools like
exec, read_file, get_info.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Command Line | Command Line |
| Quality signal | 56/100 · Good | 56/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | Not declared |
| Pricing | Not declared | Not declared |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 27 | 1 |
| Directory activity | 2 views 0 installs 0 upvotes | 1 views 0 installs 0 upvotes |
| Tools | 8 | 15 |
| Full listing | View AI Cli MCP | View Remote Agents |
Tools & capabilities
AI Cli MCP tools 8
runExecutes a prompt using Claude CLI, Codex CLI, Antigravity CLI (Gemini), OpenCode, Grok, or Pi. The appropriate CLI is automatically selected based on the model name.waitWaits for multiple AI agent processes to complete and returns their combined results. Blocks until all specified PIDs finish or a timeout occurs.peekStarts 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 `include_tool_calls` or `--include-tool-calls` to also include normalized tool-call events. It is…list_processesLists all running and completed AI agent processes with their status, PID, and basic info.doctorChecks 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.modelsLists supported model names and aliases, including models discovered by running `pi --list-models` and `opencode models`. This returns the same structured payload as `ai-cli models`. The `pi` and `opencode` arrays retain their default keys and append names ready for `run`.get_resultGets the current output and status of an AI agent process by PID.kill_processTerminates a running AI agent process by PID.
Remote Agents tools 15
execRun a shell command (locally or on a remote agent via `agent_id`)read_fileFile operations (write requires Edit/Bypass)get_infoInspect / change an agent's mode at runtimegit_statusGit operationsschedule_addCron-style tasks on a hosttask_dispatchAutonomous AI tasks run with the host's own credentialssession_listBrowse the host's AI-chat history (claude / opencode / codex / cline / roo / kilo / zed / cursor / gemini / qwen / goose / continue); `session_get` fetches a transcript or a window around one messagesession_searchFull-text search over the host's AI-chat history — a local Tantivy (BM25) index of every provider transcript, returning ranked cited snippets with `session_id` + message position (follow up with `session_get { around_seq }` for the context)list_agentsList agents connected to the relay roomfleet_execRun an operation across the fleet — `target = all \fleet_session_searchSearch the AI-chat history across the whole fleet: every matched host queries its local index, hits merge by score with host labelsfile_searchFind files on a host, and move a file host→host (UDP, SHA-256 verified)- +3 more on the listing page
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
AI Cli MCP
{
"mcpServers": {
"ai-cli-mcp": {
"command": "npx",
"args": [
"-y",
"--package",
"ai-cli-mcp@latest",
"ai-cli"
]
}
}
}
Remote Agents
{
"mcpServers": {
"remote-agents": {
"command": "npx",
"args": [
"-y",
"remote-agents"
]
}
}
}
Frequently asked questions
AI Cli MCP is categorized under Command Line and uses a local stdio subprocess. Remote Agents belongs to Command Line and uses a local stdio subprocess. Pick AI Cli MCP for command line work and Remote Agents for command line.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
AI Cli MCP has no declared pricing — check the project's own site. Remote Agents has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add ai-cli-mcp and remote-agents as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, AI Cli MCP has a quality signal of 56/100 (Good) with 2 views, 0 installs and 27 GitHub stars. Remote Agents has 56/100 (Good) with 1 views, 0 installs and 1 GitHub stars.