agent-shuttle-mcp
Related Servers
Alternatives to agent-shuttle-mcp
No user-submitted related servers found.
Related Servers
- FlicenseNot gradedqualityBmaintenanceAgent orchestration system that runs coding-agent sessions (Claude Code, Codex) with policy mediation and exposes tools via MCP.-
- AlicenseBqualityBmaintenanceEnables launching and supervising local Codex and Claude Code agent sessions and one-shot tasks, exposing run, list, stop, and output operations over MCP with session-scoped permissions and sandbox controls.2264 npm1MIT
- AlicenseNot gradedqualityDmaintenanceEnables MCP clients to spawn and control Codex CLI and Claude Code sessions on the host machine, with session management and filesystem access.4MIT
- AlicenseAqualityDmaintenanceWraps Claude Code as tools for MCP clients, enabling autonomous coding tasks via a 4-tool lifecycle with session management, async polling, and permission controls.457 npm21MIT
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients to run prompts across Codex CLI, Claude Code, Gemini CLI, and OpenCode through one uniform toolset, routing work based on remaining quota and tracking token and request usage in a shared ledger. It also lets users define and invoke reusable Markdown skills across supported agents.MIT
- AlicenseAqualityBmaintenanceEnables an MCP-capable coding client to list and read Codex sessions, resume or fork them, delegate persistent background coding tasks, and invoke Codex-configured models directly.8MIT
TDQS
Scored across 19 tools
Four tools perform delegation with near-identical purposes: ask_agent, submit_task (whose description is literally identical plus one sentence), ask_antigravity, and ask_codex. Likewise get_agent_info, get_codex_info, and get_antigravity_info overlap, leaving the agent to guess whether to use the generic or per-backend variant. The read-side tools (get_result, get_transcript, get_events, get_event_page) are distinguishable only by careful reading.
Almost everything follows a verb_noun snake_case pattern (get_result, submit_task, check_task, wait_task, cancel_task, list_agents, get_task_diff). Minor deviations exist: ask_antigravity/ask_codex drop the '_agent' suffix used by ask_agent, and apply_task_changes/discard_task_changes use a three-part noun phrase.
At 19 tools the surface is heavy and includes clear redundancy: ask_antigravity/ask_codex duplicate ask_agent, and get_codex_info/get_antigravity_info duplicate get_agent_info. The task lifecycle (submit/check/wait/cancel/diff/apply/discard) legitimately needs several tools, but a leaner set would be easier to navigate.
The domain is well covered end-to-end: discovery (list_agents), capability inspection, sync and async delegation, polling, waiting, cancellation, paginated results, transcripts, event journal, and diff review/apply/discard. Gaps are minor, e.g. no explicit follow-up message or task listing/cleanup operation.