← sf-architect-mcp

sf-architect-mcp bb618581d533617b358548f104c2c60dea7cdfb4

source_git · morettimarco/salesforce_architect_mcp · current release

9
Tools
3
Resources
0
Templates
3
Prompts

Observation

Observed 2026-08-25T21:00:24.226Z using mcpSecurity-inventory. Status: partial. Negotiated protocol: 2025-06-18.

Server capabilities
{
  "tools": {},
  "resources": {},
  "prompts": {}
}

Tools 9

ToolCategoryAnnotationsRisk
export_architect_sectionExport all pages in a section as a single concatenated markdown file. Writes to disk with zero context window cost. When output_path is omitted, defaults to ~/.sf-architect-mcp/exports/{section}-{language}.md.
Input schema
{
  "type": "object",
  "properties": {
    "section": {
      "type": "string",
      "description": "The section to export (e.g. 'fundamentals', 'well-architected')."
    },
    "output_path": {
      "type": "string",
      "description": "Optional: absolute file path. Defaults to ~/.sf-architect-mcp/exports/{section}-{language}.md."
    },
    "language": {
      "type": "string",
      "description": "Language short code (e.g. 'en', 'it', 'de'). Default: 'en'."
    }
  },
  "required": [
    "section"
  ]
}
— · —
get_scrape_statusGet the current status of the indexed database: total pages, chunks, sections breakdown, last scrape run info, and pending/failed URL counts.
Input schema
{
  "type": "object",
  "properties": {}
}
— · —
get_section_summaryGet a quick overview of a section: page count, total word count, and list of page titles. Useful for orientation before exporting or reading individual pages.
Input schema
{
  "type": "object",
  "properties": {
    "section": {
      "type": "string",
      "description": "The section name (e.g. 'fundamentals', 'well-architected')."
    },
    "language": {
      "type": "string",
      "description": "Language short code. Default: 'en'."
    }
  },
  "required": [
    "section"
  ]
}
— · —
list_architect_sectionsList all indexed sections with page counts and titles. Optionally filter to a specific section.
Input schema
{
  "type": "object",
  "properties": {
    "section": {
      "type": "string",
      "description": "Optional: filter to a specific section name."
    },
    "language": {
      "type": "string",
      "description": "Language short code (e.g. 'en', 'it', 'de'). Default: 'en'."
    }
  }
}
— · —
read_architect_pageRead the markdown content of a specific indexed Salesforce Architect page by its URL. Use max_chars to limit output size. For a lightweight overview without full content, prefer read_architect_page_summary instead.
Input schema
{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "The exact URL of the page to read."
    },
    "max_chars": {
      "type": "number",
      "description": "Optional: truncate output to this many characters. Omit for full content."
    }
  },
  "required": [
    "url"
  ]
}
— · —
read_architect_page_summaryGet a lightweight summary of an indexed page: title, section, word count, section headings, and a short preview (~500 chars). Use this to understand a page before deciding to read the full content.
Input schema
{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "The exact URL of the page."
    }
  },
  "required": [
    "url"
  ]
}
— · —
scrape_fullFull refresh: wipe all indexed data, re-fetch the sitemap from architect.salesforce.com, and re-scrape and reindex every page. Use this for initial setup or when you want a clean slate.
Input schema
{
  "type": "object",
  "properties": {
    "language_filter": {
      "type": "string",
      "enum": [
        "en",
        "dk",
        "de",
        "es",
        "fi",
        "fr",
        "it",
        "jp",
        "kr",
        "no",
        "nl",
        "ru",
        "se",
        "pt-br",
        "zh-cn",
        "zh-tw",
        "es-mx",
        "all"
      ],
      "description": "Language to scrape. 'en' (default, English), 'dk' (Danish), 'de' (German), 'es' (Spanish), 'fi' (Finnish), 'fr' (French), 'it' (Italian), 'jp' (Japanese), 'kr' (Korean), 'no' (Norwegian), 'nl' (Dutch), 'ru' (Russian), 'se' (Swedish), 'pt-br', 'zh-cn', 'zh-tw', 'es-mx', or 'all'."
    },
    "concurrency": {
      "type": "number",
      "description": "Number of parallel browser tabs (1-5). Default: 3."
    }
  }
}
— · —
scrape_incrementalIncremental scrape: fetch the sitemap, scrape any new pages not previously indexed, retry previously failed pages, and re-check existing pages for content changes. Only re-indexes pages whose content has actually changed.
Input schema
{
  "type": "object",
  "properties": {
    "language_filter": {
      "type": "string",
      "enum": [
        "en",
        "dk",
        "de",
        "es",
        "fi",
        "fr",
        "it",
        "jp",
        "kr",
        "no",
        "nl",
        "ru",
        "se",
        "pt-br",
        "zh-cn",
        "zh-tw",
        "es-mx",
        "all"
      ],
      "description": "Language to scrape. Same codes as scrape_full. Default: 'en'."
    },
    "concurrency": {
      "type": "number",
      "description": "Number of parallel browser tabs (1-5). Default: 3."
    }
  }
}
— · —
search_architect_docsSearch the locally indexed Salesforce Architect documentation. Returns ranked results with excerpts. The database must be populated first via scrape_full or scrape_incremental.
Input schema
{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Search query text."
    },
    "section": {
      "type": "string",
      "description": "Optional: filter by section (well-architected, fundamentals, decision-guides, reference-diagrams, well-architected-tools, resources)."
    },
    "max_results": {
      "type": "number",
      "description": "Maximum results to return (1-20). Default: 5."
    }
  },
  "required": [
    "query"
  ]
}
— · —

Resources 3

Resource templates 0

Prompts 3

Let’s talk about MCP security.

Share your details and our security team will contact you.