mcp-server

Page Monitors

alterlab_monitor

Destructive

Manage change monitors. action=create watches a URL on a cron schedule and notifies by webhook when content changes; action=list returns your monitors; action=delete removes one by monitor_id (it stops running and cannot be restored). Each check spends credits like a scrape.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>"
    },
    "name": "alterlab_monitor"
  }
}

Input Schema

Name	Required	Description
`url`	No	create: URL to watch
`name`	No	create: monitor name
`limit`	No	Page size (default 20)
`action`	Yes	create, list or delete
`offset`	No	Items to skip
`formats`	No	create: output formats to compare
`timezone`	No	create: timezone for the cron expression (default UTC)
`diff_mode`	No	create: how changes are detected; fields tracks typed values and needs monitor_fields
`notify_on`	No	create: send the webhook on change only, or on every check
`monitor_id`	No	delete: monitor id from create or list
`active_only`	No	list: only active items
`webhook_url`	No	create: HTTPS endpoint to notify
`check_interval`	No	create: cron expression, e.g. '0 /6 * *' (every 6 hours)
`monitor_fields`	No	create: when diff_mode=fields, {name: {selector\|xpath\|jsonld, type: number\|currency\|text\|bool, min_change: {abs\|pct}}}. Change events carry field_changes; history at GET /v1/monitors/{id}/fields/{field}/history
`monitor_selectors`	No	create: CSS selectors to track when diff_mode=selector

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedNov 9, 2026

changedInput schema / properties / diff_mode / description

Previous value: -"create: how changes are detected"New value: +"create: how changes are detected; fields tracks typed values and needs monitor_fields"

changedInput schema / properties / diff_mode / enum

Previous value: -[
-  "semantic",
-  "exact",
-  "selector"
-]New value: +[
+  "semantic",
+  "exact",
+  "selector",
+  "fields"
+]

addedInput schema / properties / monitor_fields

Added value: +{
+  "additionalProperties": {
+    "type": "object"
+  },
+  "description": "create: when diff_mode=fields, {name: {selector|xpath|jsonld, type: number|currency|text|bool, min_change: {abs|pct}}}. Change events carry field_changes; history at GET /v1/monitors/{id}/fields/{field}/history",
+  "type": "object"
+}

AddedNov 5, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already flag destructiveHint=true and non-idempotency, so the bar is lower, yet the description still adds value: it states that delete stops the monitor and is unrecoverable, and that recurring checks consume credits continuously. It does not mention auth requirements, rate limits, or what a webhook payload looks like, but the key irreversible side effect is disclosed.

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?

A single front-loaded lead sentence followed by three semicolon-delimited action clauses and a cost note — dense but readable, with no filler. Slightly telegraphic phrasing ('it stops running') but nothing wasted.

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

Completeness3/5

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

This is a high-complexity tool (15 params, nested object, three enums, no output schema), and the description covers the create/list/delete lifecycle plus cost but says nothing about what list returns (fields, pagination behavior with limit/offset) or what a monitor object looks like. With no output schema to fall back on, an agent cannot predict the response shape.

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 documents all 15 parameters, including nested monitor_fields details and cron examples. The description contributes only the action-to-parameter mapping at a high level, adding little beyond what the structured field descriptions already provide, so the baseline 3 applies.

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

Purpose4/5

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

The description names the resource (change monitors) and enumerates the three supported operations with concrete semantics for each (create watches a URL on a cron, list returns monitors, delete removes by monitor_id). It never names a sibling tool, so an agent must infer for itself why it should pick this over alterlab_schedule or the alterlab_feed_* family, which is the one thing keeping this below a 5.

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?

Each action carries enough context to select it: create implies ongoing watching, list implies retrieval, delete implies teardown. The credit note ('each check spends credits like a scrape') is a real decision aid for cost-sensitive agents. What is missing is explicit exclusions — nothing says when to use alterlab_schedule or feeds instead of a monitor.

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

All mcp-server 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.