kimi-swarm-bridge
Related Servers
Alternatives to kimi-swarm-bridge
- AlicenseDqualityBmaintenanceEnables Codex to delegate implementation tasks to Kimi Code while managing server lifecycle and authentication automatically.111MIT
Related Servers
- FlicenseNot gradedqualityCmaintenanceEnables integrating an AI-powered agile squad with MCP-compatible clients like Antigravity, Claude Desktop, and Cursor over Stdio or SSE.-
- AlicenseAqualityDmaintenanceBridges any MCP client (like Claude Code, Zed, VS Code) to any ACP coding agent, enabling multi-agent orchestration from a single chat interface.24140 npm9Apache 2.0
- AlicenseNot gradedqualityBmaintenanceBridges Kimi Code CLI to OpenAI Computer Use, enabling Kimi to control local macOS applications via MCP.6 npm6MIT
- AlicenseNot gradedqualityCmaintenanceMCP server for cross-platform agent onboarding. Registers external agents, translates intents from LangChain, CrewAI, AutoGen, and A2A formats, and proxies cross-ecosystem transactions.MIT
- AlicenseAqualityCmaintenanceMCP server that turns Kimi K2.6 Turbo into an agentic coding assistant with tools for file operations, shell commands, and code search.42MIT
- AlicenseNot gradedqualityCmaintenanceExposes authorized ChatGPT, DeepSeek, Kimi, and Grok web sessions to agents as MCP tools, including chat and local file attachments over HTTP or stdio.4MIT
TDQS
Scored across 11 tools
Each tool targets a distinct step in the Kimi task lifecycle—submit, wait, retrieve, review, continue, abort, and discover—with clear separations like async vs sync delegation and filtered vs unfiltered session listing. No two tools have overlapping purposes that would cause misselection.
All tools follow a consistent kimi_ prefix with snake_case verb_noun or verb_phrase patterns (e.g., delegate_task, get_handoff, wait_until_idle, recent_sessions). The naming is uniform and predictable, making it easy to infer each tool's role.
Eleven tools is well-scoped for a bridge server that must cover lifecycle management (delegate, wait, retrieve, review, continue, abort), session discovery, and status/diff utilities. Each tool earns its place with no redundancy.
The surface covers the full lifecycle end-to-end: submission (async and sync), waiting, retrieving results, reviewing, continuing, aborting, discovering sessions, and checking bridge health. No obvious gaps or dead ends exist for the intended purpose.