agent-intern
Related Servers
Alternatives to agent-intern
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceAn MCP server that bridges CLI coding agents like Claude Code, Codex, opencode, and Antigravity into any MCP client, enabling synchronous and asynchronous task execution, follow-up input, and a structured code review tool.41 npm2MIT
- AlicenseAqualityDmaintenanceMCP server that spawns autonomous Claude Code agents in GitHub repos, enabling task delegation with persistent state, multi-step workflows, and job monitoring.4796 npm2Apache 2.0
- FlicenseBqualityDmaintenanceMCP server that gives AI coding agents (Claude Code, Cursor, Cline, etc.) access to multiple AI models through Antigravity CLI and OpenAI Codex CLI, enabling mid-conversation model consultation and code review.8-
- AlicenseAqualityCmaintenanceAn MCP server and HTTP gateway that dispatches coding tasks to Claude Code, Codex, and Antigravity CLI sessions, keeps track of those sessions, and optionally runs an implement → review → verify loop against a real repository.6MIT
- AlicenseNot gradedqualityAmaintenanceMCP server that bridges Claude with KiloCode, enabling Claude to act as architect and delegate coding tasks to Kilo's fast CLI agent while monitoring progress and reviewing results.MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that lets Claude Code call the Google Antigravity CLI (agy) headlessly for a second opinion from a different model family, or to have agy read project files on Claude's behalf so large files never enter Claude's context window.15 npmMIT
TDQS
Scored across 29 tools
Each backend has clearly distinct ask, continue, and status tools, and the swarm/image tools are also well-differentiated. No two tools appear to do the same thing; descriptions make boundaries explicit.
All names use snake_case and most follow a backend_action pattern (e.g., antigravity_ask, codex_continue). The swarm and image tools (agent_swarm, swarm_presets, antigravity_image) deviate slightly but remain readable and predictable.
29 tools is heavy for the server's purpose. The ask/continue/status triples across eight backends are largely repetitive and could be consolidated via a backend parameter, making the surface feel bloated.
The server covers the full ask/continue/status lifecycle for each backend plus swarm and image generation, leaving few gaps. Missing tool-based preset management and session cleanup are minor limitations.