Skip to main content
Glama

ikeytz Einsatzgebiet-Karten

get_llms_mcp_server

Read-only

WHAT: Alias of get_discovery(which=llms-mcp-server) — machine/catalog text for the maps MCP server. Optional offset/limit. USE when an agent needs the server-side llms MCP catalog. NEXT: get_llms_mcp_web, get_links.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum items or lines to return after offset. Omit = all remaining in the window (subject to tool-specific clamps). For geo near-search default is often 5 without radius_km, up to 52 with radius.
offsetNo0-based index into a list or discovery file lines (split on \n). 0 = first. Omit = 0. Combine with limit to page. Use nextOffset / offset+limit from a previous result when present.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
okYestrue = use summary, canonicalUrl, and extra keys. false = do not invent data; read error + hint and retry with valid args or open hint.
bodyNoUTF-8 text window after offset/limit
hintNoPresent when ok=false. Absolute URL or short recovery hint the agent should open or pass to another tool.
pathNoPublic relative path of the file on maps
textNoAlias/window of body when present
toolYesEcho of the tool name that produced this object (e.g. get_service_area).
errorNoPresent when ok=false. Codes include: unknown_place, unknown_discovery, unknown_doc, q_required, plz_required, coords_required, outside_service_area, url_required, not_maps_host, bad_url, path_or_url_required, serp_not_found, slug_or_coords_required, path_required.
limitNoApplied line limit, or null if omitted
whichNoResolved discovery id (ard, ai-catalog, llms, robots, sitemap-txt, llms-mcp-server, …).
localeNoLocale actually used for URLs. maps is German-only: always de (MAPS-E8 — no /en on maps). Requested non-de is ignored; payload locale=de.
offsetNoApplied 0-based line offset
missingNotrue if the discovery file was not found on disk
relatedNoAlways includes https://maps.ikeytz.com/llms.txt.
summaryNoPrimary text for the model. For discovery tools this is the file window. For list tools a compact one-liner. Quote with attribution.
attributionYesRequired citation: 'Quelle: Schlüsseldienst Ludwigsburg ikeytz (ikeytz.com) · ai-train=no · https://maps.ikeytz.com/.well-known/ai.txt'
total_linesNoLine count of the full file
canonicalUrlNoBest URL to show the user: https://maps.ikeytz.com… page, public embed JSON, tel:+49…, mailto:…, https://wa.me/…, or a www pointer. Prefer this over constructing URLs.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • addedInput schema / properties / limit / description
      Added value: +"Maximum items or lines to return after offset. Omit = all remaining in the window (subject to tool-specific clamps). For geo near-search default is often 5 without radius_km, up to 52 with radius."
    • addedInput schema / properties / limit / minimum
      Added value: +1
    • addedInput schema / properties / offset / default
      Added value: +0
    • addedInput schema / properties / offset / description
      Added value: +"0-based index into a list or discovery file lines (split on \\n). 0 = first. Omit = 0. Combine with limit to page. Use nextOffset / offset+limit from a previous result when present."
    • addedInput schema / properties / offset / minimum
      Added value: +0
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "additionalProperties": true,
      +  "description": "Always the same envelope. tools/call returns content[0].text = summary (or JSON) AND structuredContent = this object. On success ok=true with summary + canonicalUrl + extra fields. On failure ok=false with error (snake_case code) and hint (recovery URL). Never writes, never submits forms, never books. Attribution must be kept when quoting. Policy: ai-input yes with attribution; ai-train=no. Host is maps.ikeytz.com (geo/Einsatzgebiet). Prices/FAQ/legal HTML live on www — maps only points.",
      +  "properties": {
      +    "attribution": {
      +      "description": "Required citation: 'Quelle: Schlüsseldienst Ludwigsburg ikeytz (ikeytz.com) · ai-train=no · https://maps.ikeytz.com/.well-known/ai.txt'",
      +      "type": "string"
      +    },
      +    "body": {
      +      "description": "UTF-8 text window after offset/limit",
      +      "type": "string"
      +    },
      +    "canonicalUrl": {
      +      "description": "Best URL to show the user: https://maps.ikeytz.com… page, public embed JSON, tel:+49…, mailto:…, https://wa.me/…, or a www pointer. Prefer this over constructing URLs.",
      +      "type": "string"
      +    },
      +    "error": {
      +      "description": "Present when ok=false. Codes include: unknown_place, unknown_discovery, unknown_doc, q_required, plz_required, coords_required, outside_service_area, url_required, not_maps_host, bad_url, path_or_url_required, serp_not_found, slug_or_coords_required, path_required.",
      +      "type": "string"
      +    },
      +    "hint": {
      +      "description": "Present when ok=false. Absolute URL or short recovery hint the agent should open or pass to another tool.",
      +      "type": "string"
      +    },
      +    "limit": {
      +      "description": "Applied line limit, or null if omitted",
      +      "type": [
      +        "number",
      +        "null"
      +      ]
      +    },
      +    "locale": {
      +      "description": "Locale actually used for URLs. maps is German-only: always de (MAPS-E8 — no /en on maps). Requested non-de is ignored; payload locale=de.",
      +      "enum": [
      +        "de"
      +      ],
      +      "type": "string"
      +    },
      +    "missing": {
      +      "description": "true if the discovery file was not found on disk",
      +      "type": "boolean"
      +    },
      +    "offset": {
      +      "description": "Applied 0-based line offset",
      +      "type": "number"
      +    },
      +    "ok": {
      +      "description": "true = use summary, canonicalUrl, and extra keys. false = do not invent data; read error + hint and retry with valid args or open hint.",
      +      "type": "boolean"
      +    },
      +    "path": {
      +      "description": "Public relative path of the file on maps",
      +      "type": "string"
      +    },
      +    "related": {
      +      "description": "Always includes https://maps.ikeytz.com/llms.txt.",
      +      "items": {
      +        "format": "uri",
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    "summary": {
      +      "description": "Primary text for the model. For discovery tools this is the file window. For list tools a compact one-liner. Quote with attribution.",
      +      "type": "string"
      +    },
      +    "text": {
      +      "description": "Alias/window of body when present",
      +      "type": "string"
      +    },
      +    "tool": {
      +      "description": "Echo of the tool name that produced this object (e.g. get_service_area).",
      +      "type": "string"
      +    },
      +    "total_lines": {
      +      "description": "Line count of the full file",
      +      "type": "number"
      +    },
      +    "which": {
      +      "description": "Resolved discovery id (ard, ai-catalog, llms, robots, sitemap-txt, llms-mcp-server, …).",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "ok",
      +    "tool",
      +    "attribution"
      +  ],
      +  "type": "object"
      +}
  2. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, and the description adds the disclosure that this is an alias of get_discovery and returns 'machine/catalog text'. This gives useful semantic context beyond the structured fields, though it does not describe pagination clamps or output formatting in detail.

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?

The description is compact, labeled, and front-loaded with WHAT, USE, and NEXT. Every clause provides actionable information with no filler.

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?

The tool is simple, has an output schema, readOnlyHint annotation, and the description covers its alias relationship, purpose, and next-step siblings. Nothing an agent needs to select and invoke it correctly is missing.

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 the parameters are already fully documented. The description only restates that offset/limit are optional and does not add substantive meaning beyond the schema.

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 it is an alias of get_discovery(which=llms-mcp-server) for serving the maps MCP catalog, which is a specific verb+resource. The reference to sibling tools get_llms_mcp_web and get_links helps differentiate it from neighboring retrieval tools.

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?

Explicitly states when to use it ('USE when an agent needs the server-side llms MCP catalog') and points to follow-on alternatives with 'NEXT'. It stops short of explicitly naming situations where another sibling should be chosen instead, so it is clear context without full exclusions.

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