Stormap
AI visibility score, AI crawler checks, llms.txt and robots.txt generators, AI agent guides.
使うべきか
品質と安全性
検出事項（1）
- LOWTool 'get_guide' description lacks action verbget_guide 内
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"stormap": {
"url": "https://stormap.ai/mcp"
}
}
}リモートエンドポイント
https://stormap.ai/mcpstreamable-httpできること
ツール一覧
ツール（6）
🟢search_guides(query, category, limit)
Search Stormap's practical guides on building with AI agents (OpenClaw, Hermes, Claude, coding agents, browser automation, RAG, MCP, AI news). Returns titles, URLs, Markdown URLs and short descriptions. Use get_guide to read one.
入力スキーマ
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "What to look for, e.g. \"install hermes desktop\" or \"stop coding agents overwriting files\"."
},
"category": {
"type": "string",
"description": "Optional category filter, e.g. \"OpenClaw Tutorials\", \"AI News\", \"AI Tools\", \"Automation\"."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 20,
"default": 5
}
},
"required": [
"query"
],
"additionalProperties": false
}🟢get_guide(slug, max_chars)
Return one Stormap guide as clean Markdown with front matter (title, URL, dates, tags). Accepts a slug ("how-to-install-hermes-desktop") or a stormap.ai post URL.
入力スキーマ
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "Guide slug or full https://stormap.ai/post/... URL."
},
"max_chars": {
"type": "integer",
"minimum": 1000,
"maximum": 200000,
"default": 60000
}
},
"required": [
"slug"
],
"additionalProperties": false
}🟢ai_visibility_score(url)
Score how well AI assistants (ChatGPT, Claude, Perplexity, Gemini) can find, read and cite a public web page: 0-100 score, letter grade, pass/fail checks (AI answer-bot access in robots.txt, server-rendered content, title/meta, JSON-LD, canonical, llms.txt, sitemap) and a prioritized fix list. Blocking bulk training crawlers is treated as a policy choice and does not lower the score.
入力スキーマ
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Public page URL or domain, e.g. \"example.com\" or \"https://example.com/pricing\"."
}
},
"required": [
"url"
],
"additionalProperties": false
}🟢check_ai_crawler_access(url)
Check whether AI crawlers (GPTBot, ChatGPT-User, OAI-SearchBot, ClaudeBot, Claude-User, PerplexityBot, Google-Extended, CCBot) may access a public URL according to its robots.txt, and score the page's machine readability (status, title, meta description, canonical, JSON-LD, server-rendered text). Returns a 0-100 score and a list of findings.
入力スキーマ
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Public page URL or domain, e.g. \"https://example.com/pricing\"."
}
},
"required": [
"url"
],
"additionalProperties": false
}🟢generate_llms_txt(site_url, site_name, summary, pages, max_pages)
Generate an llms.txt file (llmstxt.org format) for a public website. Uses the site name, summary and pages you pass; anything missing is filled from the homepage and sitemap.xml. Returns the file text plus notes on how to improve it.
入力スキーマ
{
"type": "object",
"properties": {
"site_url": {
"type": "string",
"description": "Site root, e.g. \"https://example.com\"."
},
"site_name": {
"type": "string"
},
"summary": {
"type": "string",
"description": "One paragraph: what the site is, who it is for, what is most useful."
},
"pages": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 100,
"description": "Optional list of the most important page URLs. If omitted, sitemap.xml is used."
},
"max_pages": {
"type": "integer",
"minimum": 5,
"maximum": 60,
"default": 25
}
},
"required": [
"site_url"
],
"additionalProperties": false
}🟢generate_ai_robots_txt(policy, overrides, allow_paths, disallow_paths, sitemap_url, ...)
Generate robots.txt rules for AI crawlers from a policy: "open" (allow all), "balanced" (allow search and user-triggered fetchers, block bulk training crawlers) or "block" (block all). Optional per-bot overrides, allowed/blocked paths, sitemap and crawl delay. No network access.
入力スキーマ
{
"type": "object",
"properties": {
"policy": {
"type": "string",
"enum": [
"open",
"balanced",
"block"
],
"default": "balanced"
},
"overrides": {
"type": "object",
"additionalProperties": {
"type": "string",
"enum": [
"allow",
"block"
]
},
"description": "e.g. {\"GPTBot\":\"allow\",\"CCBot\":\"block\"}"
},
"allow_paths": {
"type": "array",
"items": {
"type": "string"
}
},
"disallow_paths": {
"type": "array",
"items": {
"type": "string"
}
},
"sitemap_url": {
"type": "string"
},
"crawl_delay": {
"type": "integer",
"minimum": 1,
"maximum": 60
},
"site_url": {
"type": "string"
}
},
"additionalProperties": false
}コミュニティ
エビデンス