io.github.lazymac2x/agent-workflow-engine is an MCP server published by io.github.lazymac2x, hosted at api.lazy-mac.com. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 5 tools, including create_workflow, track_agent_state, get_workflow_status, auto_route_next_step, set_conditional_branch.
Cloudflare Workers MCP server: agent-workflow-engine
160 connections through 5 shared values. Tap any node.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
Create a new multi-agent workflow. Returns a workflow_token encoding the full state — pass it to all subsequent calls.
| Parameter | Type | Description |
|---|---|---|
| name * | string | Workflow name |
| steps | array | Ordered step sequence (agent IDs) |
| agents * | array | Agent IDs in this workflow |
{
"name": "create_workflow",
"description": "Create a new multi-agent workflow. Returns a workflow_token encoding the full state — pass it to all subsequent calls.",
"inputSchema": {
"type": "object",
"required": [
"name",
"agents"
],
"properties": {
"name": {
"type": "string",
"description": "Workflow name"
},
"steps": {
"type": "array",
"items": {
"type": "string"
},
"description": "Ordered step sequence (agent IDs)"
},
"agents": {
"type": "array",
"items": {
"type": "string"
},
"description": "Agent IDs in this workflow"
}
}
}
}Update agent execution state. Returns updated workflow_token.
| Parameter | Type | Description |
|---|---|---|
| error | string | Error message (if failed) |
| output | object | Agent output payload |
| status * | string | one of ["pending","running","completed","failed"] |
| agent_id * | string | Agent identifier |
| workflow_token * | string | Token from create_workflow or previous call |
| execution_time_ms | number | Execution time in ms |
{
"name": "track_agent_state",
"description": "Update agent execution state. Returns updated workflow_token.",
"inputSchema": {
"type": "object",
"required": [
"workflow_token",
"agent_id",
"status"
],
"properties": {
"error": {
"type": "string",
"description": "Error message (if failed)"
},
"output": {
"type": "object",
"description": "Agent output payload"
},
"status": {
"enum": [
"pending",
"running",
"completed",
"failed"
],
"type": "string"
},
"agent_id": {
"type": "string",
"description": "Agent identifier"
},
"workflow_token": {
"type": "string",
"description": "Token from create_workflow or previous call"
},
"execution_time_ms": {
"type": "number",
"description": "Execution time in ms"
}
}
}
}Decode a workflow_token and return full status summary.
| Parameter | Type | Description |
|---|---|---|
| workflow_token * | string | Token encoding workflow state |
{
"name": "get_workflow_status",
"description": "Decode a workflow_token and return full status summary.",
"inputSchema": {
"type": "object",
"required": [
"workflow_token"
],
"properties": {
"workflow_token": {
"type": "string",
"description": "Token encoding workflow state"
}
}
}
}Advance to the next workflow step, evaluating conditional branches. Returns next_agent and updated workflow_token.
| Parameter | Type | Description |
|---|---|---|
| workflow_token * | string | Current workflow token |
| current_agent_output | object | Output from last agent. Used for conditional branch evaluation. |
{
"name": "auto_route_next_step",
"description": "Advance to the next workflow step, evaluating conditional branches. Returns next_agent and updated workflow_token.",
"inputSchema": {
"type": "object",
"required": [
"workflow_token"
],
"properties": {
"workflow_token": {
"type": "string",
"description": "Current workflow token"
},
"current_agent_output": {
"type": "object",
"description": "Output from last agent. Used for conditional branch evaluation."
}
}
}
}Attach a conditional branch to a step. Operator is evaluated against agent output when routing. Returns updated workflow_token.
| Parameter | Type | Description |
|---|---|---|
| step_index * | integer | Step index to attach condition to |
| workflow_token * | string | Current workflow token |
| condition_logic * | object |
{
"name": "set_conditional_branch",
"description": "Attach a conditional branch to a step. Operator is evaluated against agent output when routing. Returns updated workflow_token.",
"inputSchema": {
"type": "object",
"required": [
"workflow_token",
"step_index",
"condition_logic"
],
"properties": {
"step_index": {
"type": "integer",
"description": "Step index to attach condition to"
},
"workflow_token": {
"type": "string",
"description": "Current workflow token"
},
"condition_logic": {
"type": "object",
"required": [
"operator",
"true_agent"
],
"properties": {
"field": {
"type": "string",
"example": "success",
"description": "Output field to evaluate"
},
"value": {
"description": "Comparison value for equals/gte/lte/contains operators"
},
"operator": {
"enum": [
"equals",
"not_equals",
"truthy",
"falsy",
"gte",
"lte",
"contains"
],
"type": "string"
},
"true_agent": {
"type": "string",
"description": "Agent ID if condition is true"
},
"description": {
"type": "string",
"description": "Human-readable description"
},
"false_agent": {
"type": "string",
"description": "Agent ID if condition is false"
}
}
}
}
}
}Names, descriptions and schemas were written by the server and are shown as data.
Pattern matches on what the server declares. They show what it says it can do, not what it does.
None yet. Changes appear after a server's second daily check.