Agent Orchestrator MCP
- Updated June 26, 2026
- CSOAI-ORG/agent-orchestrator-mcp
Agent Orchestrator MCP is a MCP server that lets your coding agent coordinate multi-step MEOK agent workflows through stdio MCP tools.
About
Agent Orchestrator MCP is a stdio Model Context Protocol server from MEOK AI Labs that gives coding agents a control plane to run multi-step agent workflows instead of manually chaining prompts. developers shipping agent-first SaaS or internal automation install it when one session must launch, monitor, or sequence worker agents with repeatable MCP calls. Skillselion shelves it under build / agent-tooling with operate / infra as a secondary home for the same orchestration graph once it runs on a schedule or in production. The published registry entry is lean; the GitHub repo carries the authoritative tool list and configuration. Treat it as orchestration infrastructure—use alongside negotiation or router MCPs when your architecture splits concerns. Intermediate to advanced depending on how many branches, failures, and external MCPs you attach. It is not a hosted no-code workflow UI; it is protocol-level orchestration your agent invokes directly.
- MEOK AI Labs agent-orchestrator-mcp for coordinating agent workflows over MCP
- Stdio MCP package agent-orchestrator-mcp v1.0.3 on PyPI
- GitHub repository CSOAI-ORG/agent-orchestrator-mcp for implementation details
- Pairs naturally with agent-mcp-router-mcp for large MEOK fleets
- Central place to trigger multi-step agent runs from Claude Code or Cursor
Agent Orchestrator MCP by the numbers
- Data as of Aug 10, 2026 (Skillselion catalog sync)
claude mcp add agent-orchestrator-mcp -- uvx agent-orchestrator-mcpAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| Package | agent-orchestrator-mcp |
|---|---|
| Transport | STDIO |
| Auth | None |
| Last updated | June 26, 2026 |
| Repository | CSOAI-ORG/agent-orchestrator-mcp ↗ |
What it does
Orchestrate multiple MEOK-compatible agents and MCP tools from one MCP server while you ship agent-native products.
Who is it for?
Best when you're composing several MEOK MCP agents and want a single orchestration entry point in Claude Code or Cursor.
Skip if: Simple single-tool projects that never spawn secondary agents or long-running graphs.
What you get
After registration, your primary agent can start, advance, and manage orchestrated worker flows via dedicated MCP tools.
- Orchestration MCP tools for starting and managing agent workflow runs
- Repeatable multi-agent execution path wired into your dev or prod agent host
By the numbers
- Version 1.0.3 stdio package on PyPI with GitHub source CSOAI-ORG/agent-orchestrator-mcp
README.md
Agent Orchestrator MCP
Multi-agent task management: create agents, delegate tasks with trust-based routing, coordinate f...
Multi-agent task management: create agents, delegate tasks with trust-based routing, coordinate file access, run sprints, and monitor performance.
🚀 Quick Start
# Install via pip
pip install agent_orchestrator_mcp
# Or install via Smithery
npx -y @smithery/cli@latest install agent-orchestrator-mcp --client claude
✨ Features
- Multi-agent task management
- Dependency resolution
- Parallel execution
- Retry & backoff
- Progress tracking
📖 Documentation
🛡️ Compliance
This MCP server is built with EU AI Act compliance built-in:
- ✅ Article 9 — Risk Management System
- ✅ Article 13 — Transparency & Instructions for Use
- ✅ Article 15 — Bias Detection & Testing
- ✅ Article 26 — FRIA Support (where applicable)
- ✅ Article 50 — AI Content Watermarking (where applicable)
Need help getting compliant? Book a free 15-min diagnostic →
🏢 Enterprise
Need custom development, SLA guarantees, or white-label deployment?
- Pro: $99/mo — Full MCP suite + EU AI Act tracking
- Enterprise: $499/mo — Custom dev + SLA + Dedicated support
View Pricing → | Contact Sales →
🤝 Part of the MEOK Ecosystem
This server is part of the MEOK AI Labs ecosystem — 300+ MCP servers for sovereign AI governance.
| Domain | Purpose |
|---|---|
| councilof.ai | EU AI Act compliance marketplace |
| safetyof.ai | AI safety & monitoring |
| meok.ai | Sovereign AI platform |
| cobolbridge.ai | Legacy modernization |
📜 License
MIT © CSOAI-ORG
Built with 💜 by MEOK AI Labs · UK Companies House 16939677
💸 Try MEOK in 30 seconds — instant buy ladder
| Tier | Price | What you get | Stripe |
|---|---|---|---|
| Smoke test | £1 | Signed sample MCP-Hardening report + Article 50 PDF | https://buy.stripe.com/aFa7sNcgAdQS0ZT1Uc8k91t |
| Quick Kit | £9 | EU AI Act Article 50 implementation guide (C2PA + EU-Icon) | https://buy.stripe.com/aFa7sNcgAdQS0ZT1Uc8k91t |
| Founder Call | £29 | 30-min 1-on-1 with the founder | https://buy.stripe.com/aFa7sNcgAdQS0ZT1Uc8k91t |
Refundable. UK Stripe — VAT-clean. Builds on the 81-MCP MEOK fleet. Verify any signed report at https://meok.ai/verify.
Configuration
Add to your claude_desktop_config.json (Claude Desktop) or your MCP client config:
{
"mcpServers": {
"agent-orchestrator-mcp": {
"command": "uvx",
"args": ["agent-orchestrator-mcp"]
}
}
}
Or: pip install agent-orchestrator-mcp then run the agent-orchestrator-mcp command (stdio transport).
Examples
Once configured, ask your assistant, for example:
- "Use
create_agentto …" - "Use
list_agentsto …" - "Use
delegate_taskto …"
See also
MEOK compliance MCP fleet:
agent-commerce-protocol-mcp, agent-cost-allocator-mcp, agent-identity-trust-mcp, agent-replay-debugger-mcp, agent-x402-paywall-mcp
Recommended MCP Servers
0Latency Memory MCPPersistent memory layer for AI agents.
0nMCP — Universal AI API OrchestratorUniversal AI API Orchestrator — 1,554 tools, 96 services.
0xHumans Protocol MCPMCP for AI agents: financing, skills, lending on Base1k Patient MCP1k patient MCP server
1trippulse MCP1trip PULSE: 21-tool AI travel planner.
3D AI Agent Avatar MCP3D AI Agent Avatar — render any GLB, give it a Solana wallet, a voice, and pump.fun powers.90How it compares
Agent workflow orchestrator MCP, not a CI pipeline skill or a static project plan document.
FAQ
Who is agent-orchestrator-mcp for?
It is for developers and small teams who run multi-agent MEOK stacks and need MCP-native orchestration from their main coding agent.
When should I use agent-orchestrator-mcp?
Use it when building agent-tooling that requires sequenced or parallel agent steps, and keep it wired in operate when those graphs run against live infra.
How do I add agent-orchestrator-mcp to my agent?
Install agent-orchestrator-mcp from PyPI, configure stdio in your MCP host, and follow CSOAI-ORG/agent-orchestrator-mcp on GitHub for orchestration tools and env vars.