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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.