Statistical Process Control & Anomaly Alerts

Process Monitor — Get Engine Script (long histories)

process_monitor_get_engine

Read-only

For more than 20,000 metric rows, or any such file already in your code sandbox. Returns a complete numpy-only Python script with the same engine as process_monitor; it reads the metric rows, optional per-metric settings and stored limits, prints the decision cards and one status line per metric, and writes everything to process_check.json. No metric data reaches this server on this path.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "process_monitor_get_engine"
  }
}

Input Schema

Name	Required	Description
`params`	No	Other inputs exactly as process_monitor takes them (rules, subgroup_by ...).
`limits_path`	No	Optional stored limits file.
`series_path`	No	Metric rows file (CSV/TSV/JSON).
`metrics_path`	No	Optional per-metric settings file.

Output Schema

Name	Required	Description	Default
`notes`	No
`paths`	No
`script`	Yes
`language`	No
`requires`	No
`writes_file`	No
`instructions`	Yes
`engine_version`	Yes
`scipy_required`	No
`data_requirements`	No
`network_access_required`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 30, 2026

TDQS

A4.1/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/openWorld/non-destructive, and the description adds real behavioral context beyond that: the script's inputs, that it prints decision cards plus one status line per metric, that it writes process_check.json, and the notable data-flow fact that no metric data reaches the server. Strong transparency, though execution environment assumptions are left implicit.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the selection condition before describing output, which is the useful ordering. Dense but nearly every clause carries information; the long middle sentence is slightly run-on but earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present and 100% parameter coverage, the description's job is to cover the trigger condition and script behavior, which it does. Covers conditions, inputs, outputs, and the privacy property; minor gaps remain around sandbox execution expectations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema already labels each path (metric rows, per-metric settings, stored limits) and the nested params object. The description restates these file roles without adding format or syntax detail, so it only marginally exceeds baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: returns a complete numpy-only Python script replicating the process_monitor engine. It explicitly distinguishes itself from the sibling by naming 'the same engine as process_monitor', so an agent can tell the two apart without opening schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit triggering condition — 'For more than 20,000 metric rows, or any such file already in your code sandbox' — which strongly implies process_monitor is the alternative for smaller data. It stops short of stating the inverse condition or naming the fallback explicitly, keeping it at 4.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Statistical Process Control & Anomaly Alerts tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.