Agent Delegation MCP
- Updated June 26, 2026
- CSOAI-ORG/agent-delegation-mcp
Agent Delegation MCP is a MCP server that exposes delegation workflows so coding agents can assign subtasks to other agents via MCP.
About
Agent Delegation MCP is a Model Context Protocol server from MEOK AI Labs that gives developers a concrete hook for delegating work between agents instead of improvising nested prompts in every session. If you are building agent-first products or internal coding stacks, you install it during the Build phase as agent-tooling: it exposes delegation-oriented capabilities your primary agent can call while planning refactors, parallel research, or specialist subtasks. The distribution matches other CSOAI-ORG servers—a PyPI stdio package at version 1.0.4—so registration in Claude Code, Cursor, or Codex-compatible clients follows the same path as your other MCP tools. It complements certified handoff and identity servers when you want structured delegation before you add cryptographic provenance. Treat it as orchestration plumbing, not a replacement for your own task definitions or supervisor logic.
- MEOK AI Labs MCP server focused on agent-to-agent delegation patterns
- PyPI package agent-delegation-mcp with stdio transport (v1.0.4)
- Fits Claude Code / Cursor style multi-agent coding setups
- Part of the CSOAI-ORG agent governance toolkit alongside handoff and identity servers
- Python-packaged server for local MCP registration
Agent Delegation MCP by the numbers
- Data as of Aug 10, 2026 (Skillselion catalog sync)
claude mcp add agent-delegation-mcp -- uvx agent-delegation-mcpAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| Package | agent-delegation-mcp |
|---|---|
| Transport | STDIO |
| Auth | None |
| Last updated | June 26, 2026 |
| Repository | CSOAI-ORG/agent-delegation-mcp ↗ |
What it does
Structure how one coding agent delegates subtasks to another without ad-hoc prompt chains that lose context.
Who is it for?
Best when you're experimenting with supervisor–worker agent architectures in Claude Code or Cursor and want MEOK’s delegation primitives on stdio.
Skip if: Skip if you only need a single monolithic agent with no sub-agent routing, or those requiring signed handoff provenance without pairing other MEOK MCP servers.
What you get
You register delegation tools in your agent so subtask assignment follows a repeatable MCP contract instead of one-off instructions.
- Registered MCP delegation server (v1.0.4) in your local agent config
- Callable delegation tools usable from primary agent sessions
By the numbers
- Server version 1.0.4
- PyPI identifier agent-delegation-mcp
- Transport: stdio
README.md
Agent Delegation MCP
Create and delegate tasks to specialized agents, track progress, and manage task lifecycle
Create and delegate tasks to specialized agents, track progress, and manage task lifecycle. Supports priority queuing and capability-based agent matching.
🚀 Quick Start
# Install via pip
pip install agent_delegation_mcp
# Or install via Smithery
npx -y @smithery/cli@latest install agent-delegation-mcp --client claude
✨ Features
- MCP protocol compliant
- Easy installation
- Well-documented API
- Production-ready
- Active maintenance
📖 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
Each tier above the free self-host adds HMAC-signed attestations verifiable at `verify.meok.ai`. Linux Foundation governance on the A2A spine means EU regulated buyers can deploy without vendor-lock-in objections.💸 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-delegation-mcp": {
"command": "uvx",
"args": ["agent-delegation-mcp"]
}
}
}
Or: pip install agent-delegation-mcp then run the agent-delegation-mcp command (stdio transport).
Examples
Once configured, ask your assistant, for example:
- "Use
create_taskto …" - "Use
delegate_taskto …" - "Use
get_task_statusto …"
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 orchestration MCP, not a general LLM API proxy or a project-management integration.
FAQ
Who is Agent Delegation MCP for?
Developers building multi-agent coding or automation flows who want MCP-native delegation instead of custom orchestration scripts.
When should I use Agent Delegation MCP?
Use it while building agent-tooling—when you split research, implementation, and review across agents and need consistent delegation calls.
How do I add Agent Delegation MCP to my agent?
Install agent-delegation-mcp from PyPI, add it to your MCP server config with stdio transport, and restart your Claude Code or Cursor session.