Lossless-Codex-Orchestrator 是 AI Skill Hub 本期精选MCP工具之一。综合评分 8.0 分,整体质量较高。我们强烈推荐将其纳入你的 AI 工具库,帮助提升工作效率。
Lossless-Codex-Orchestrator 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
Lossless-Codex-Orchestrator 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/100yenadmin/Lossless-Codex-Orchestrator-LCO
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"lossless-codex-orchestrator": {
"command": "npx",
"args": ["-y", "lossless-codex-orchestrator-lco"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 Lossless-Codex-Orchestrator 执行以下任务... Claude: [自动调用 Lossless-Codex-Orchestrator MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"lossless-codex-orchestrator": {
"command": "npx",
"args": ["-y", "lossless-codex-orchestrator-lco"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
LCO turns local Codex sessions into searchable, bounded, approval-aware work objects for OpenClaw.

Use it when an agent or user needs to answer: what sessions are active, what did they plan, what did they finish, what files did they touch, and what is the next safe action without rereading raw transcripts.
| What LCO gives agents | Why it matters |
|---|---|
| Searchable local session memory | Find plans, finals, touched files, and refs without raw transcript rereads. |
| Bounded evidence expansion | Read compact public-safe briefs before opening larger source material. |
| Approval-gated boundaries | Dry-run Codex actions and verify matching audit ids before any live control. |
| OpenClaw/MCP tools | Use the same local-first recall and approval-bounded surfaces from agent workflows. |
Setup · Contributing · Agent Instructions · Agent Skill · OpenClaw Plugin · Security · Code of Conduct · Vision · Privacy · Claude Boundary · Claim Audit · QA Lab · Release Notes · 1.2.4 Notes · 1.2.3 Notes · 1.2.2 Notes · 1.2.1 Notes · 1.2.0 Notes · 1.1.4 Notes · 1.0 Notes · License
Requirements:
~/.codex/sessionsloo_* tools through OpenClawStable install:
npm install -g lossless-openclaw-orchestrator@latest
loo doctor
Beta train, when you explicitly want the newest prerelease:
npm install -g lossless-openclaw-orchestrator@beta
Package channels:
latest is the stable public channel.beta is the active prerelease train.next is reserved for release candidates.Full first-run instructions live in docs/SETUP.md.
Search for a session:
loo search "billing bridge proposed plan"
Describe a result:
loo describe codex_thread:<thread-id>
Expand a bounded brief:
loo expand-ref --profile brief --token-budget 1000 codex_thread:<thread-id>
Expand from a query when you do not know the ref yet:
loo expand-query --profile brief --token-budget 1000 "billing bridge"
For normal agent workflows, start with the compact public/operator facade instead of treating every loo_* tool as a peer:
| Step | Tool | Purpose |
|---|---|---|
| 1 | loo_prepared_inbox | Start from the compact prepared-state operating picture. |
| 2 | loo_describe_ref | Look up a specific session or source ref from the inbox. |
| 3 | loo_expand_query | Expand one bounded evidence brief when the ref is not known. |
| 4 | loo_recent_sessions | Refresh recent or active cards after reads or approved actions. |
| 5 | loo_attention_inbox | Review the compact attention queue before choosing a next action. |
| 6 | loo_project_digest | Produce a bounded provenance and handoff digest. |
| 7 | loo_codex_control_dry_run | Create the exact dry-run action packet and approval hashes. |
| 8 | loo_codex_resume_thread | Run an approved resume only after the matching audit id. |
Other declared tools remain available as workflow_detail, proof_debug, or internal_low_level surfaces for setup, diagnosis, proof, and recovery. Their existence is deliberate: normal agents should start from the facade, then drop to the lower tiers only when the compact path returns a specific next step or blocker.
loo_codex_control_dry_run returns the audit id and hashes an agent should show before any live start/resume/send/steer/interrupt call. Live control requires the matching approval_audit_id.
Live Codex control results include proof_state fields for accepted_by_transport, started, completed, persisted, and unverified_pending. Transport acceptance is not durable execution: when unverified_pending is true, run the returned next_proof read-only tool call before claiming the turn or thread completed, persisted, or is safe to build on.
The packaged agent playbook is skills/lossless-openclaw-orchestrator/SKILL.md.
Naming policy: LCO is the public product abbreviation and lco_* is the forward public alias target for new user-facing tool names. The currently callable OpenClaw/MCP tools still use the historical loo_* runtime prefix, so examples that must run today continue to show loo_* until #434 lands a tested alias layer. Do not delete or silently rename the loo_* tools; keep them as backward-compatible aliases when lco_* aliases are added.
高质量的MCP工具,自动化编码辅助和审批
该工具使用 NOASSERTION 协议,商用场景请仔细阅读协议条款,必要时咨询法律意见。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
📄 NOASSERTION — 请查阅原始协议条款了解具体使用限制。
经综合评估,Lossless-Codex-Orchestrator 在MCP工具赛道中表现稳健,质量优秀。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | Lossless-Codex-Orchestrator-LCO |
| 原始描述 | 开源MCP工具:Index, search, summarize, and approval-gate local Codex sessions through OpenCla。⭐69 · TypeScript |
| Topics | mcpagent-toolsai-agentsai-coding-assistantcodexcodex-clitypescript |
| GitHub | https://github.com/100yenadmin/Lossless-Codex-Orchestrator-LCO |
| License | NOASSERTION |
| 语言 | TypeScript |
收录时间:2026-07-05 · 更新时间:2026-07-05 · License:NOASSERTION · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端