Skip to main content
Glama
Sign In
BlueMonkey262

subagent-mcp

by BlueMonkey262
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript

Related Servers

Alternatives to subagent-mcp

No user-submitted related servers found.

    Related Servers

    • nuncius

      sdirkse
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables Claude Code, Codex, and Cursor to delegate self-contained coding tasks to one another on the user's own subscriptions, with each task isolated in a git worktree and sandbox, usage tracked, budgets enforced, and results returned for review.
      438 npm
      2
      Apache 2.0

    • claude-agy

      ronisaguey-ux
      A
      license
      A
      quality
      C
      maintenance
      Enables an agent to drive Claude Code and Antigravity (agy) sessions as controlled subagents — listing, spawning, messaging, interrupting, waiting on, and stopping them, including fan-out of several at once. It also provides a locked, fsynced bridge so separate agents can exchange messages.
      19
      MIT

    • Moderator MCP Server

      linyh1983
      F
      license
      Not graded
      quality
      D
      maintenance
      Allows users to manage multiple remote AI coding agents from a single Claude Code session, with a controlled execution model where operations require moderator approval.
      -

    • claude-opencode-mcp-v2

      choruzo
      A
      license
      A
      quality
      B
      maintenance
      Enables Claude Code to delegate software-engineering tasks to OpenCode agents running in the same workspace/worktree, with the model and provider chosen per agent. Exposes tools for task delegation, persistent sessions, diffs, and agent listing so an orchestrator can research, edit, review, and test code.
      7
      249 npm
      MIT

    • Standalone Agent Orchestrator

      muratangin187
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables MCP clients to delegate work to nested subagents running on Codex and Claude Code, keeping each task's session, turn history and results durable in SQLite while the main chat continues. Supports async or blocking waits, mid-session context updates, git worktree isolation, read-only-by-default permission inheritance, and cancelling whole subagent trees.
      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

    A3.7/5.0

    Scored across 14 tools

    Disambiguation4/5

    Most tools have clearly distinct purposes across the subagent lifecycle: spawning, messaging, listing, polling events, retrieving results, waiting, approving, and cleanup. The main possible confusion is between stop_agent and stop_agents, but their descriptions distinguish single-agent interruption from batch/group cancellation; list_agents versus list_agent_configs is also distinguishable but close enough to require attention.

    Naming Consistency5/5

    All tools use consistent snake_case verb_noun naming, such as spawn_agent, send_message, get_agent_events, list_agents, stop_agent, and cleanup_worktree. The singular/plural distinction in stop_agent and stop_agents is a deliberate scope difference rather than a naming inconsistency.

    Tool Count5/5

    Fourteen tools is well within the appropriate range for a subagent orchestration server and each tool maps to a meaningful lifecycle operation. There is no obvious padding or missing core action at the count level.

    Completeness5/5

    The set covers the full subagent lifecycle: discovery, spawning, resuming via messaging, event polling, waiting, result retrieval, approval resolution, stopping, cleanup, and routing memory. Listing models and configs plus recording outcomes and notes also supports operational decision-making and observability.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources