Skip to main content
Glama
mkXultra

ai-cli-mcp

by mkXultra
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Related Servers

Alternatives to ai-cli-mcp

No user-submitted related servers found.

    Related Servers

    • all-agents-mcp

      Dokkabei97
      A
      license
      B
      quality
      F
      maintenance
      Enables orchestrating multiple AI CLI agents (Claude Code, Codex, Gemini CLI, Copilot CLI) through a unified MCP interface for task delegation, cross-agent comparison, and specialized tools like code review and debugging.
      14
      17 npm
      14
      MIT

    • llm-router-mcp

      Kijun0708
      A
      license
      D
      quality
      B
      maintenance
      Enables Claude Code as a team leader to delegate tasks to GPT and Gemini experts, supporting multi-LLM collaboration with tools for consultation, code review, design, and background execution.
      76
      23 npm
      MIT

    • Zen MCP Server

      salvadorthebrown
      F
      license
      Not graded
      quality
      Not graded
      maintenance
      Orchestrates multiple AI models (Gemini, OpenAI, Claude, local models) within a single conversation context, enabling collaborative workflows like multi-model code reviews, consensus building, and CLI-to-CLI bridging for specialized tasks.
      -
    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A3.7/5.0

    Scored across 9 tools

    Disambiguation4/5

    Most tools have clearly distinct roles: run spawns, kill_process terminates, list_processes enumerates, doctor checks binaries, models lists models, cleanup_processes prunes. The monitoring trio of get_result, peek, and wait overlaps somewhat, but the descriptions draw explicit boundaries (wait is batch, peek is a one-shot observation window, get_result is current status/output).

    Naming Consistency4/5

    All names use snake_case consistently, with a mild verb_noun flavor for the process-management tools (get_result, list_processes, kill_process, cleanup_processes). A few are bare nouns/verbs (run, peek, doctor, models), which is a minor deviation but still readable and predictable.

    Tool Count5/5

    Nine tools is well-scoped for a CLI agent orchestration server, with each tool earning its place across the start/monitor/finish/cleanup lifecycle. Nothing feels padded or redundant enough to cut.

    Completeness4/5

    The async process lifecycle is fully covered: spawn (run), enumerate (list_processes), observe (peek, get_result), await (wait), terminate (kill_process), and prune (cleanup_processes), plus discovery/health via models and doctor. Minor gaps exist, such as no explicit way to send follow-up input or steer a running agent, but core workflows are complete.

    Maintenance

    ActivityActive
    ResponsivenessUnresponsive

    Resources