Skip to main content
Glama

kadi_bence/sitemap-extractor

kadi_bence--sitemap-extractor
Destructive

This tool calls the Actor "kadi_bence/sitemap-extractor" and retrieves its output results. Actor description: Extract every URL from a website's XML sitemaps. Input: websites or sitemap URLs; optional URL globs, date filter, status check, new-URLs-only monitor. Returns per URL: url, lastmod, changefreq, priority, images, hreflang, source sitemap. Default: 20 URLs per site. $0.30/1k URLs.

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": "kadi_bence--sitemap-extractor"
  }
}

Input Schema

NameRequiredDescriptionDefault
waitSecsNoMax seconds (0–45, default 30) to cap the wait for the Actor run to reach terminal state. For long-running Actors the response returns at the cap with the current run status; follow `nextStep` to poll via get-actor-run. Set to 0 to fire-and-forget.
startUrlsNoA website (apify.com) or a sitemap file (https://example.com/sitemap.xml). For a website the Actor reads the Sitemap: lines in robots.txt, then tries the usual paths. Nested sitemap indexes and .gz files are followed. Example values: [{"url":"https://apify.com"}]
checkStatusNoSends one HEAD request per URL and adds status, finalUrl and redirectCount. Slower. Same price.
monitorNameNoUse different names to keep separate histories. Example values: "default"default
onlyNewUrlsNoReturn only URLs not returned by an earlier run. Schedule it to get new pages of a site or a competitor.
excludeGlobsNoShell-style patterns, e.g. */tag/*.
includeGlobsNoShell-style patterns matched against the full URL or path, e.g. /blog/*. Empty keeps everything.
maxUrlsPerSiteNoStop after this many URLs per site. You pay per URL saved. Example values: 20
modifiedWithinDaysNoKeep URLs whose lastmod is at most this old. URLs without a lastmod are dropped when this is set.
proxyConfigurationNoUsually not needed. If a site blocks the Actor, try the datacenter Apify Proxy. Residential proxies are not supported. Example values: {"useApifyProxy":false}

Output Schema

NameRequiredDescriptionDefault
tipNoAdvisory guidance RAG Web Browser wrote to its key-value store under the reserved "TIP" key
runIdYesActor run ID
statsNoRun statistics
statusYesRun status: READY | RUNNING | TIMING-OUT | TIMED-OUT | ABORTING | ABORTED | SUCCEEDED | FAILED
actorIdYesStable Apify Actor ID from the run record
summaryYesPast-tense summary of the run state
exitCodeNoActor process exit code; populated for terminal states (especially FAILED)
nextStepYesOne primary follow-up action with identifiers interpolated
storagesYesDataset and key-value store metadata, keyed by alias. "default" is always the primary entry.
actorNameNo"username/actor-name"
startedAtNoISO timestamp when the run started
finishedAtNoISO timestamp when the run finished (terminal states only)
statusMessageNoPass-through from Apify run.statusMessage
apifyConsoleUrlNoPersonalized Apify Console link to the run; present only for Console sessions

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedOutput schema / properties / storages / properties / datasets / properties / default / properties / itemsSchema
      Added value: +{
      +  "description": "JSON Schema for rows in the dataset at `storages.datasets.default.id` — describes row shape only; the rows themselves are NOT returned inline in this response. Inferred from this Actor's historical successful runs. To fetch actual rows, call `get-dataset-items` with the dataset id and a `fields` projection drawn from this schema.",
      +  "properties": {
      +    "alternates": {
      +      "items": {},
      +      "type": "array"
      +    },
      +    "changefreq": {
      +      "type": "null"
      +    },
      +    "imageCount": {
      +      "type": "number"
      +    },
      +    "lastmod": {
      +      "type": "null"
      +    },
      +    "priority": {
      +      "type": "null"
      +    },
      +    "site": {
      +      "type": "string"
      +    },
      +    "sitemapUrl": {
      +      "type": "string"
      +    },
      +    "url": {
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
  2. First observed

TDQS

B3.4/5.0
Behavior3/5

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

The description adds concrete behavioral facts not present in the annotations: the $0.30/1k URL price, the default cap of 20 URLs per site, and that a monitor keeps per-name history across runs. However, annotations declare destructiveHint=true and readOnlyHint=false, and the description never explains what is actually mutated (dataset writes, persisted monitor state) or that runs may return at the waitSecs cap with a polling nextStep. No contradiction, but a notable gap against the destructive flag.

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

Conciseness3/5

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

The second sentence is dense and informative, but the opening sentence is pure plumbing that consumes front-loaded attention without telling an agent anything about the capability. The remaining content is appropriately sized for a 10-parameter Actor, with no obvious padding beyond that wrapper.

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 need not restate return fields, and it still summarizes them usefully. Complexity is moderate (10 params, nested request-list and proxy objects, monitor state), and the description covers the essentials, missing only the long-running/polling behavior and what state persists between monitor runs.

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 description coverage is 100%, so every parameter is already documented in structured form, setting a baseline of 3. The prose summary mirrors those parameters (globs, date filter, status check, monitor) without adding syntax, interaction rules, or precedence detail beyond the schema. The cost and default figures it repeats are also present in the schema defaults.

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 a specific verb and resource: 'Extract every URL from a website's XML sitemaps', plus a clear input/output summary. It distinguishes itself implicitly from audit-style siblings by being a pure URL enumerator, though it never names a sibling explicitly. The wrapper sentence ('calls the Actor ... retrieves its output results') is boilerplate but does not obscure the purpose.

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

Usage Guidelines3/5

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

Usage context is implied rather than stated: it tells you the inputs can be a website or a sitemap file and that a monitor mode exists for tracking new URLs, which hints at when it is useful. There is no explicit when-to-use versus alternatives such as seo-site-audit or ai-readiness-audit, and no exclusion guidance. An agent must infer the routing decision from the resource name alone.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.