Multi-agent workflow orchestrator with MCP tool servers: planner/executor agents, tool-use loop, MCP client/server, tracing and durable runs.
View on GitHub ↗Production-grade multi-agent workflow orchestrator built on the Model Context Protocol (MCP). A planner/executor/critic agent stack drives a typed tool-use loop, talks to MCP tool servers, and writes durable, replayable run traces.
Most agent frameworks stop at a chat loop. agent-workflow-mcp goes further: deterministic planning, structured tool calls, MCP-native tool discovery, retries with backoff, durable run state, and a trace log you can replay end-to-end. Designed to run unattended for hours and pick up where it left off after a crash.
- Planner / Executor / Critic agents that decompose a goal into a typed plan, dispatch tool calls, and critique each step before committing. - MCP client + server transport over stdio and WebSocket, with full JSON-RPC 2.0 protocol support and capability negotiation. - Tool-use loop with bounded retries, exponential backoff, schema validation, and a stop-on-criteria hook so loops cannot run away. - Durable run state: every step, tool call, and intermediate message is appended to an event log that can be replayed or resumed. - OpenTelemetry-style tracing with span IDs, parent links, token accounting, and latency histograms per agent role. - Typed config via Pydantic v2 with profile-based overrides (default, dev, prod). - Pluggable providers: built-in Anthropic adapter with a clean Provider protocol for OpenAI, Bedrock, or local backends. - CLI with serve, run, replay, trace subcommands and JSON output for scripting. - 92% test coverage, property-based tests for the retry and replay logic.
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/tainguyen07--agent-workflow-mcp.html)
A hands-on, step-by-step workshop for building a Travel Assistant agent on Microsoft Foundry hosted agents with the Agent Framework - growing from a single agent to a multi-agent planner with function
modulastack/modula-relayLocal MCP relay for cross-model agent teams. Your Claude, Codex, and other agents talk to each other over Unix sockets. No broker, no network, no accounts.
polaris-smart/mcd-agent-gourmet麦门点餐议事会：用官方 MCP 整单核价，让预算、口味、营养数据三种意见透明比较。免 Token 网页体验，Python 零依赖。
wahyunuriman999/Muse-Skill-HubOpen-source, LLM-agnostic capability runtime for AI agents — 97 skills as typed, permission-enforced MCP tools. Final certification: 23/23 gates PASS.
menma4ever/agentic-team-mcpAutonomous hierarchical multi-agent team (CEO -> Manager -> Workers) for Model Context Protocol (MCP). Mix Claude Code, Antigravity, Codex & Direct API with persistent SQLite queues and a real-time we
Alex663028/pulse-agentPulse — Hermes-style self-improving AI agent. Reliability-first rebuild with evaluated skill self-evolution, multi-agent team orchestration, dialectic user modeling, and fully self-hosted default stac
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.