Skip to main content
Glama

Bestehende Website übernehmen

import_starten

Spiegelt eine bestehende Website in diese Website hinein: holt, was sie ausliefert, rechnet die Verweise auf relative Pfade um und macht daraus EINE Version. Vorher muss import_vorbereiten gelaufen und der Nachweis eingerichtet sein. WICHTIG, dem Kunden vorher sagen: Übernommen wird das ausgelieferte Ergebnis, nicht das CMS – aus WordPress oder TYPO3 wird statisches HTML, Formulare haben danach kein Backend, und gemeinsame Teile wie Kopf und Fuss stehen danach in jeder Seite einmal. Der Lauf läuft im Hintergrund; der Stand kommt über import_status.

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": {
      "website": "<website>",
      "url": "<url>"
    },
    "name": "import_starten"
  }
}

Input Schema

NameRequiredDescriptionDefault
artNoWelchen Nachweis der Kunde eingerichtet hat. Ohne Angabe werden beide versucht.
urlYesStartadresse der bestehenden Website, z. B. «https://alte-seite.ch/». Gelesen werden nur ihre öffentlichen Seiten per HTTP GET, wie ein Browser sie abruft – kein API-Aufruf, keine Zugangsdaten.
websiteYesKennung oder Name der Website. Reicht der Zugang ueber mehrere Organisationen und gibt es die Kennung mehrfach, «organisation/website» schreiben.
ersetzenNoNur nötig, wenn in dieser Website schon Dateien liegen – sie werden dann überschrieben.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Adds substantial behavior beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true): the run is asynchronous in the background, the delivered HTML output is imported rather than the CMS, forms lose their backend, and shared header/footer parts are duplicated into every page. That is exactly the kind of consequence an agent must warn the customer about, and it does not conflict with the declared hints.

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

Conciseness5/5

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

Front-loaded with the verb and the transformation, then prerequisites, then the customer-facing warning, then the async note. Every sentence carries a distinct fact; nothing is repeated from the title or schema.

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

Completeness5/5

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

No output schema exists, and the description compensates by explaining where the run status comes from (import_status) and what the end state looks like (static HTML, one copy of shared parts per page). For a four-parameter, open-world import tool this covers everything needed to call it safely.

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%, so all four parameters are already documented, including the enum values for «art» and the meaning of «ersetzen». The description adds context about the imported result (served pages only, no credentials) but no parameter-level detail beyond the schema, so the baseline of 3 applies.

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 concrete verb and resource: mirrors an existing website into this one, fetching what it serves and rewriting references to relative paths to produce one version. It also distinguishes itself from siblings by naming import_vorbereiten as a prerequisite and import_status as the progress channel, so an agent can place it without opening other 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 a clear precondition (import_vorbereiten must have run and the proof/«Nachweis» must be set up) and routes progress polling to import_status. What is missing is a when-not: nothing says what to do if the target already contains files beyond the parameter note about overwriting, and no explicit exclusion condition is stated.

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.

Resources