otaman-bus-server
Provides a stdio MCP server for single-user local operation of the otaman platform, enabling agent orchestration, slash commands, and skill management within Claude Code without a remote bridge daemon.
README
otaman-plugin
Otaman platform: otaman-core · otaman-cli · otaman-plugin (you are here) · otaman-bridge · otaman-runner · otaman-adapters
Otaman's Claude Code plugin — slash commands, skills, agent definitions, hook scripts, and the stdio MCP fallback server. Marketplace-installable; works standalone or as the client side of a full otaman deployment.
Full documentation, walkthroughs, and architecture notes live at docs.otaman.ai.
What this plugin provides
- Plugin manifest —
plugin.json/mcp.jsondeclaring the plugin to Claude Code. - Slash commands — every
/otaman:<cmd>the human or agents invoke in a Claude Code session. - Skills — reusable instructional modules:
multi-repo-orchestration,spec-management,cto-advisor,ba-skill,cpo-skill, and others. - Agent definitions — observer and reviewer personas (cto-reviewer, security-observer, spec-validator) that Claude Code instantiates on demand.
- Hook scripts — Bash + Python scripts wired into Claude Code's
PreToolUse,SessionStart,Stop, andPreCompactlifecycle events. - stdio MCP server — runs in-process when no bridge daemon is present, enabling single-user local operation.
- Launcher scripts —
launch-agents.sh(Linux / macOS) andlaunch-agents.ps1(Windows) for multi-agent session start-up.
Dependencies
- Claude Code (the harness)
otaman-core(shared protocols, identity resolution, secret-source chain)otaman-bridgeat runtime for remote-approval AFK mode and bus routing (optional — degrades gracefully to stdio MCP)
Quick start (development)
# Install with dev + test extras
uv sync --package otaman-plugin --extra test
# Run the test suite
uv run --package otaman-plugin pytest
# Install the plugin into Claude Code (from plugin root)
claude mcp add otaman-plugin --transport stdio -- python -m otaman_plugin.servers.bus_server
To wire the hooks, add the hooks.json entries from hooks/hooks.json to your project's .claude/settings.json, with CLAUDE_PLUGIN_ROOT pointing at this repo's checkout.
Repository layout
| Directory | Contents |
|---|---|
src/otaman_plugin/ |
Python modules — MCP servers (servers/), discovery, scaffolding, doctor checks |
scripts/ |
Hook scripts + multi-platform launchers |
agents/, skills/, commands/ |
Claude Code plugin assets — subagents, skills, slash commands |
hooks/ |
hooks.json and the auxiliary scripts wired to Claude Code lifecycle events |
profiles/ |
Skill profiles (healthcare, software-development, minimal-meta) |
templates/ |
Companion-repo templates used during project scaffolding |
examples/ |
Worked example of a otaman-managed project layout |
references/ |
User-facing setup, walkthrough, and reference documentation |
archive/ |
Internal-only material kept in-tree for project history (not user-facing) |
tests/ |
pytest suite |
See also
- docs.otaman.ai — full documentation, walkthroughs, architecture notes, and integration guides
references/getting-started.md— getting started inside this reporeferences/launcher-walkthrough.md— launcher quick referenceCONTRIBUTING.md— contributor workflowSECURITY.md— security policy and reporting channel
License
AGPL-3.0 (community edition). Commercial license available for teams that cannot ship source — see otaman.ai.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。