Cloudflare Workers MCP server: agent-trace-auditor
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 audit of an agent execution trace. Detects infinite loops, duplicate calls, tool errors, cost overruns, schema violations, and latency bottlenecks. Returns verdict (pass/review/block), score 0-100, and detailed findings.
Agent execution steps. Each step: {tool, input, output, model, ts, latency_ms, error}
Cost cap in USD (default 5.0)
Per-tool required field schemas for input validation
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Full audit of an agent execution trace. Detects infinite loops, duplicate calls, tool errors, cost overruns, schema violations, and latency bottlenecks. Returns verdict (pass/review/block), score 0-100, and detailed findings.
| Argument | Type | Description |
|---|
| trace* | array | Agent execution steps. Each step: {tool, input, output, model, ts, latency_ms, error} |
| budget_usd | number | Cost cap in USD (default 5.0) |
| tool_schemas | object | Per-tool required field schemas for input validation |
{
"type": "object",
"required": [
"trace"
],
"properties": {
"trace": {
"type": "array",
"items": {
"type": "object",
"properties": {
"ts": {
"type": "string"
},
"tool": {
"type": "string"
},
"error": {},
"input": {},
"model": {
"type": "string"
},
"output": {},
"latency_ms": {
"type": "number"
}
}
},
"description": "Agent execution steps. Each step: {tool, input, output, model, ts, latency_ms, error}"
},
"budget_usd": {
"type": "number",
"description": "Cost cap in USD (default 5.0)"
},
"tool_schemas": {
"type": "object",
"description": "Per-tool required field schemas for input validation"
}
}
}Compare two agent traces to detect regressions. Returns score delta, cost delta, added/removed tools, new/resolved issue types.
| Argument | Type | Description |
|---|---|---|
| trace_a* | array | Baseline (previous) trace |
| trace_b* | array | New trace to compare against baseline |
| budget_usd | number |
{
"type": "object",
"required": [
"trace_a",
"trace_b"
],
"properties": {
"trace_a": {
"type": "array",
"description": "Baseline (previous) trace"
},
"trace_b": {
"type": "array",
"description": "New trace to compare against baseline"
},
"budget_usd": {
"type": "number"
}
}
}Fast pass/review/block verdict with score and issue counts. Use in CI gates.
| Argument | Type | Description |
|---|---|---|
| trace* | array | Agent execution steps |
| budget_usd | number |
{
"type": "object",
"required": [
"trace"
],
"properties": {
"trace": {
"type": "array",
"description": "Agent execution steps"
},
"budget_usd": {
"type": "number"
}
}
}