Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@OmniAgent MCP Mesh Create a DAG workflow to run code review and deploy to production"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An enterprise-grade, asynchronous Multi-Agent Orchestration & Model Context Protocol (MCP) Router Mesh framework in Python.
Asynchronous DAG Engine: High-performance, concurrent Directed Acyclic Graph execution with automatic deadlock detection, cycle validation, retry policies, and timeouts.
Model Context Protocol (MCP) Router: Standardized JSON-RPC 2.0 transport router for registering and dispatching tool invocations across LLM agent swarms.
Consensus-Driven Agent Swarms: Multi-agent role hierarchy (Planner, Coder, Evaluator, Security Auditor) with asynchronous consensus broadcasting.
Semantic Vector-Graph Memory: Hybrid context store for dynamic session state persistence and RAG retrieval.
REST & Telemetry Gateway: Built-in FastAPI server for remote execution, system health monitoring, and tool management.
Production Ready: Includes Docker containerization, docker-compose, GitHub Actions CI/CD pipeline, and full Pytest coverage.
Related MCP server: JamJet
┌─────────────────────────────────┐
│ FastAPI REST Gateway │
└────────────────┬────────────────┘
│
┌────────────────▼────────────────┐
│ MCP Router Hub │
│ (JSON-RPC 2.0 Tools) │
└────────────────┬────────────────┘
│
┌─────────────────────────┼─────────────────────────┐
│ │ │
┌─────────▼──────────┐ ┌──────────▼──────────┐ ┌──────────▼──────────┐
│ Async DAG Engine │ │ Consensus Swarms │ │ Vector-Graph Store │
└────────────────────┘ └─────────────────────┘ └─────────────────────┘git clone https.github.com/ASHOKMUKHERJEE6/omni-agent-mcp-mesh.git
cd omni-agent-mcp-mesh
pip install .[dev]uvicorn omni_mesh.api.main:app --reload --port 8000docker-compose up --buildRun the full async test suite:
python -m pytestDistributed under the MIT License. See LICENSE for more information.
This server cannot be deployed
Agent-native collaboration network: orchestrate a team of long-running agents from any MCP client.
Coordinate multiple AI agents over MCP: atomic claims, leases, shared ledger, handoffs, tasks.
Control plane for autonomous software labor. Agents claim objectives over MCP with audit trail.
Workflow diagnostics, capability routing, and x402 settlement for MCP-compatible agents.
