Skip to main content
Glama
Sign In
native-agent-router

native-agent-router

by BerineYang
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to native-agent-router

No user-submitted related servers found.

    Related Servers

    • agent-hub

      LJUN0308
      A
      license
      Not graded
      quality
      C
      maintenance
      Lets a lead MCP client delegate text tasks to other LLMs and run CLI coding agents as background jobs, exposing tools to list workers, ask a model synchronously, and check status, read results, or cancel long-running tasks.
      MIT

    • Sub-Agents MCP Server

      claudiakilic58400
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables any MCP-compatible client to run reusable, Markdown-defined coding agents (such as reviewers, test writers, or investigators) through a configurable coding CLI backend, returning results into the same conversation. Agent definitions and backend/model settings can be shared across clients, and sessions can persist across multiple calls for longer work.
      315 npm
      MIT

    • agentmux

      seaweedsoup98
      A
      license
      B
      quality
      B
      maintenance
      Enables any MCP host to delegate work to multiple coding-agent CLIs such as Codex, Claude Code, and Antigravity as subagents, preserving native sessions and supporting team-based supervision and agent-to-agent messaging.
      17
      21 npm
      Apache 2.0
    • kagero

      kageroofficial

      niwa-labs
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables unified access to multiple coding-agent CLIs via MCP, with tools for running prompts, managing sessions, and retrieving task outputs.
      MIT
    Deploy Server
    Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

    TDQS

    A4.2/5.0

    Scored across 5 tools

    Disambiguation5/5

    Each tool covers a distinct lifecycle stage: agents discovers workers, run submits a unit of work, wait blocks for completion, inspect reads task details, and cancel aborts. There is no meaningful overlap or ambiguity between them.

    Naming Consistency4/5

    The verb-style names run, wait, inspect, and cancel are clear and consistently formatted. 'agents' is a minor deviation since it is a noun command rather than a verb_noun action like list_agents, but the pattern is still easy to predict.

    Tool Count5/5

    Five tools is well-scoped for the server's purpose: agent discovery, task submission, waiting, inspection, and cancellation. Each tool has a clear role and none feel redundant.

    Completeness4/5

    The core agent-routing and task lifecycle is well covered: discover agents, submit tasks, wait, inspect, and cancel. A minor gap is the lack of a task-listing or search tool if a task_id is lost, but this does not prevent normal workflows.

    Maintenance

    ActivityStale
    ResponsivenessNo recent community issues

    Resources