Development
Plan and visualise an API latency budget. Enter a P99 target (e.g. ≤ 300ms) and per-stage allocations (DNS, TCP, TLS, TTFB, Processing, Network) to see a live waterfall, budget utilisation, and over-budget warnings. Optionally paste an OpenTelemetry or Datadog trace to reverse-engineer a measured allocation.
Call this tool from your code in three languages.
curl -X POST 'https://api.elysiatools.com/en/api/tools/api-latency-budget-planner' \
-H 'Content-Type: application/json' \
-d '{"budget":300,"allocation":"DNS=5\nTCP=10\nTLS=20\nTTFB=80\nProcessing=120\nNetwork=40","slo":"p99","trace":""}'Send a POST request with your inputs as JSON. File parameters require a separate upload first.
POST https://api.elysiatools.com/en/api/tools/api-latency-budget-planner| Name | Type | Required | Description |
|---|---|---|---|
| budget | number | Yes | The overall latency target in milliseconds (e.g. 300 for P99 ≤ 300ms). |
| allocation | textarea | Yes | One stage per line as name=ms (also accepts name: ms or name ms). |
| slo | select | No | — |
| trace | textarea | No | Optional OpenTelemetry or Datadog trace JSON. The tool extracts per-span durations to suggest an allocation. |
HTML result
{
"result": "<div>Processed HTML content</div>",
"error": "Error message (optional)",
"message": "Notification message (optional)",
"metadata": {
"key": "value"
}
}Add this tool to your Model Context Protocol server so AI agents can list and call it.
Add this block to your MCP client configuration:
{
"mcpServers": {
"elysiatools-api-latency-budget-planner": {
"name": "api-latency-budget-planner",
"description": "Plan and visualise an API latency budget. Enter a P99 target (e.g. ≤ 300ms) and per-stage allocations (DNS, TCP, TLS, TTFB, Processing, Network) to see a live waterfall, budget utilisation, and over-budget warnings. Optionally paste an OpenTelemetry or Datadog trace to reverse-engineer a measured allocation.",
"baseUrl": "https://api.elysiatools.com/mcp/sse?toolId=api-latency-budget-planner",
"command": "",
"args": [],
"env": {},
"isActive": true,
"type": "sse"
}
}
}After connecting to the SSE endpoint, list the exposed tools:
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/list"
}Invoke the tool by its id, passing arguments built from its parameters:
{
"jsonrpc": "2.0",
"id": 2,
"method": "tools/call",
"params": {
"name": "api-latency-budget-planner",
"arguments": {
"budget": 300,
"allocation": "DNS=5\nTCP=10\nTLS=20\nTTFB=80\nProcessing=120\nNetwork=40",
"slo": "p99",
"trace": ""
}
}
}Questions or issues? Contact [email protected]