Skip to main content
Glama
ghl-mcp-server-v2

ghl-mcp-server-v2

by zackscriven

ghl_kb_crawler_discover

Starts a website crawl to discover pages for later AI training. Use it before ingesting selected URLs; returns operation ID, status, and crawled URL.

Instructions

Start crawling and discover pages for training Starts a website crawl that discovers pages for later AI training. WHEN TO USE: use this when you need to scan a site before training; use trainDiscoveredUrls to ingest selected pages; use getCrawlingStatusForLatestOperation to poll progress. RETURNS: the discovery operation id, current status, and the URL being crawled. Endpoint: POST /knowledge-bases/crawler (Version header: v3; source: v3/knowledge-base-v3.json) Requires a Sub-Account (location) token. OAuth scopes: knowledge-bases.write

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": {
      "body": "<body>"
    },
    "name": "ghl_kb_crawler_discover"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYesRequest body (schema carried verbatim from the official OpenAPI spec).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv2.1.0
    • addedInput schema / properties / body / properties / autoTrain
      Added value: +{
      +  "description": "Automatically train the discovered URLs after crawling",
      +  "example": false,
      +  "type": "boolean"
      +}
    • addedInput schema / properties / body / properties / preSelectedUrls
      Added value: +{
      +  "description": "Pre-selected URLs from sitemap preview — when provided, only these URLs are crawled",
      +  "example": [
      +    "https://example.com/page-1",
      +    "https://example.com/page-2"
      +  ],
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / body / title
      Added value: +"DiscoverWebsiteRequestDTO"
  2. First observedv2.0.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare openWorldHint=true and non-idempotency, and the description adds genuinely new operational facts beyond them: a Sub-Account (location) token is required, the call needs the knowledge-bases.write scope, and it kicks off an asynchronous operation whose id must be retained for polling. It would be stronger if it said whether re-invoking creates a duplicate crawl operation.

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 structure is front-loaded and sectioned (purpose, WHEN TO USE, RETURNS, endpoint, auth), which helps scanning, but the first two lines say the same thing twice ('Start crawling and discover pages for training' then 'Starts a website crawl that discovers pages...'). The trailing endpoint and OpenAPI-source metadata is boilerplate that does not help tool selection.

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 no output schema, the RETURNS line is essential and is present, telling the agent to expect an operation id and status for later polling. Auth requirements and the write scope are also covered, which is the main non-obvious prerequisite. What remains missing is the asynchronous handoff detail: how long a crawl typically takes or that no pages are usable until the poll tool reports completion.

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%, with every nested body field (url, option, autoTrain, locationId, knowledgeBaseId, preSelectedUrls) documented in the schema itself, so the baseline is 3. The description adds nothing about parameter behavior, such as what the Exact/Path/Domain option values actually scope the crawl to or the relationship between autoTrain and the separate train tool.

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 second sentence states a specific verb and resource: 'Starts a website crawl that discovers pages for later AI training.' That is materially clearer than the generic name alone, and the tool is a distinct step in a multi-stage pipeline. It stops short of a 5 because the real differentiation from siblings is deferred to the WHEN TO USE block rather than being part of the core purpose statement.

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?

The WHEN TO USE block names three concrete situations and points to the follow-on tools for training and progress polling, which tells an agent where this tool sits in the workflow. It loses a point because the referenced names ('trainDiscoveredUrls', 'getCrawlingStatusForLatestOperation') do not match the actual sibling tool names (ghl_kb_crawler_train, ghl_kb_crawler_status), and it never mentions ghl_kb_get_sitemap_preview as the alternative when you only want a preview without crawling.

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

Deploy Server

Other Tools