Cloudflare Workers MCP server: agent-loop-detector
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Full diagnostic: loop detection, cost breakdown, stuck-state classification, and fix recommendations for an AI agent trace.
Ordered array of agent steps (role, tool, input, output, tokens, model)
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Full diagnostic: loop detection, cost breakdown, stuck-state classification, and fix recommendations for an AI agent trace.
| Argument | Type | Description |
|---|---|---|
| trace* | array | Ordered array of agent steps (role, tool, input, output, tokens, model) |
| pricing | object |
{
"type": "object",
"required": [
"trace"
],
"properties": {
"trace": {
"type": "array",
"items": {
"type": "object"
},
"description": "Ordered array of agent steps (role, tool, input, output, tokens, model)"
},
"pricing": {
"type": "object",
"nullable": true,
"properties": {
"in": {
"type": "number"
},
"out": {
"type": "number"
}
}
}
}
}Calculate per-model token usage and USD cost from an agent trace. Supports custom pricing overrides.
| Argument | Type | Description |
|---|---|---|
| trace* | array | |
| pricing | object |
{
"type": "object",
"required": [
"trace"
],
"properties": {
"trace": {
"type": "array",
"items": {
"type": "object"
}
},
"pricing": {
"type": "object",
"nullable": true,
"properties": {
"in": {
"type": "number"
},
"out": {
"type": "number"
}
}
}
}
}Detect exact-call repeats, periodic tool-call cycles, and ping-pong patterns in an agent trace.
| Argument | Type | Description |
|---|---|---|
| trace* | array |
{
"type": "object",
"required": [
"trace"
],
"properties": {
"trace": {
"type": "array",
"items": {
"type": "object"
}
}
}
}