lazymac2x avatar

Agent Workflow Engine

lazymac2x/agent-workflow-engine-api

A workflow orchestration layer built on Cloudflare Workers that exposes agent task management through MCP. The server runs as a remote service over streamable HTTP, so you're not running anything locally. It's pitched as a drop-in for Claude Desktop, Cursor, and Continue with a free tier and a lifetime pro option at $19-29. The repository itself is light on implementation details, mostly configuration and tooling setup with mcpize.yaml and Wrangler config. Reach for this if you want to coordinate multi-step agent workflows without managing infrastructure yourself, though you'll want to check the actual API capabilities since the public repo doesn't expose much about what operations or state management it actually provides.

tools
5
transport
HTTP
last updated
May 16, 2026

Install

From registry metadata
$ npx add-mcp https://api.lazy-mac.com/agent-workflow-engine/mcp --name agent-workflow-engine

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http agent-workflow-engine https://api.lazy-mac.com/agent-workflow-engine/mcp

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 5 tools

Verified live against the running server on Nov 6, 2026.

create_workflowCreate a new multi-agent workflow. Returns a workflow_token encoding the full state — pass it to all subsequent calls.3 params

Create a new multi-agent workflow. Returns a workflow_token encoding the full state — pass it to all subsequent calls.

Parameters* required
agents*array
Agent IDs in this workflow
name*string
Workflow name
stepsarray
Ordered step sequence (agent IDs)
track_agent_stateUpdate agent execution state. Returns updated workflow_token.6 params

Update agent execution state. Returns updated workflow_token.

Parameters* required
agent_id*string
Agent identifier
errorstring
Error message (if failed)
execution_time_msnumber
Execution time in ms
outputobject
Agent output payload
status*string
one of pending · running · completed · failed
workflow_token*string
Token from create_workflow or previous call
get_workflow_statusDecode a workflow_token and return full status summary.1 params

Decode a workflow_token and return full status summary.

Parameters* required
workflow_token*string
Token encoding workflow state
auto_route_next_stepAdvance to the next workflow step, evaluating conditional branches. Returns next_agent and updated workflow_token.2 params

Advance to the next workflow step, evaluating conditional branches. Returns next_agent and updated workflow_token.

Parameters* required
current_agent_outputobject
Output from last agent. Used for conditional branch evaluation.
workflow_token*string
Current workflow token
set_conditional_branchAttach a conditional branch to a step. Operator is evaluated against agent output when routing. Returns updated workflow_token.3 params

Attach a conditional branch to a step. Operator is evaluated against agent output when routing. Returns updated workflow_token.

Parameters* required
condition_logic*object
step_index*integer
Step index to attach condition to
workflow_token*string
Current workflow token

Sponsors

Readme

Details

Repository
github.com/lazymac2x/agent-workflow-engine-api
Categories
AI & LLM Tools, Cloud & Infrastructure, Automation & Workflows
Transport
HTTP
Registry
MCP registry, active
Tools verified
Nov 6, 2026

More from lazymac2x

Related AI & LLM Tools MCP servers

View all
1lazymac2x avatarAi Agent Scratchpadlazymac2x/ai-agent-scratchpad-apiCloudflare Workers MCP server: ai-agent-scratchpad0stars
2pavelguzenfeld avatarGeminipavelguzenfeld/gemini-mcpMCP server that exposes Google Gemini as tools for Claude Code0stars
3pipeworx-io avatarGemini Cryptopipeworx-io/mcp-gemini-cryptoGemini Exchange MCP (public endpoints).0stars
4pipeworx-io avatarHuggingfacepipeworx-io/mcp-huggingfaceHugging Face Hub MCP — models, datasets, spaces0stars
5slashml-ai avatarSlashML (/ml) Persistent Agent Memory & Code Localizationslashml-ai/ml-memoryPersistent conversational memory, behavioral code search, and bug localization for AI agents.0stars
6sumanaddanki avatarSuma Memorysumanaddanki/suma-mcpPersistent memory for Claude Code and Cursor. Stop re-explaining your project every session.0stars