Skip to main content
Glama
yigitkonur

Super Subagents

by yigitkonur
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Related Servers

Alternatives to Super Subagents

No user-submitted related servers found.

    Related Servers

    • claude-subagents-mcp

      jordankzf
      A
      license
      A
      quality
      C
      maintenance
      Enables delegating tasks to up to four parallel Claude subagents from Codex or other stdio MCP clients, with workspace file access and per-agent model/effort configuration.
      8
      MIT

    • subturn

      eshatalov
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables any MCP client to launch and manage subagent sessions in installed coding agents like Codex, Claude Code, Grok, and OpenCode, using your existing logins and chosen models.
      280 npm
      MIT

    • OpenCode MCP Orchestrator

      Mesya82
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables MCP-capable coding assistants to delegate repository investigation, bounded implementation work, and noisy command runs (tests, builds, linters) to sandboxed OpenCode agents. Each role can use an independently selected model, and only concise results are returned to the parent agent, which keeps responsibility for architecture and high-risk operations.
      MIT

    • Polyagent MCP

      execveat
      A
      license
      Not graded
      quality
      D
      maintenance
      Enables any MCP-compatible client to use existing Claude Code agents from .claude/agents/ directories. Spawns agents in separate CLI sessions for better context optimization and performance across Codex, Gemini CLI, and other AI coding assistants.
      3
      MIT
    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

    A4.5/5.0

    Scored across 8 tools

    Disambiguation4/5

    Each agent role (researcher/planner/coder/tester/classic) and management action (message/cancel/answer) is clearly distinct. The only slight ambiguity is between message-agent and answer-agent, but their descriptions clearly separate follow-up instructions from responding to pending questions.

    Naming Consistency5/5

    All tools follow a predictable verb_noun pattern with lowercase hyphenation, and the 'launch-super-X' series is highly consistent. The deviating 'launch-classic-agent' still fits the same verb_noun structure.

    Tool Count5/5

    8 tools is well-scoped for an agent-orchestration server, covering launching, messaging, answering, and cancelling without unnecessary bloat. Each tool earns its place in the workflow.

    Completeness5/5

    The tool set covers the full agent lifecycle: launching each role (researcher, planner, coder, tester, classic), resuming via message, answering pending questions, and cancelling. Status monitoring is handled via task resources, so there are no obvious dead ends.

    Maintenance

    ActivityInactive
    ResponsivenessNo issues

    Resources