An MCP server and REST API your agents can call: check whether AI crawlers can read a site, generate llms.txt and AI robots.txt files, and search Stormap's practical guides on building with AI agents. Free to try, no signup.
https://stormap.ai/mcpsearch_guides, get_guide, ai_visibility_score, check_ai_crawler_access, generate_llms_txt, generate_ai_robots_txtYou get a free key with 500 calls/month. No card needed.
Guides & robots.txt: 200 calls/day. Visibility score, crawler check & llms.txt: 20/day. Per IP.
Need a burst? Credit pack: $10 for 1,000 extra calls, used after your monthly allowance, never expire.
claude mcp add --transport http stormap https://stormap.ai/mcp
# with a key:
claude mcp add --transport http stormap https://stormap.ai/mcp --header "Authorization: Bearer smk_YOUR_KEY"Settings → Connectors → Add custom connector → URL https://stormap.ai/mcp
{
"mcpServers": {
"stormap": {
"url": "https://stormap.ai/mcp",
"headers": { "Authorization": "Bearer smk_YOUR_KEY" }
}
}
}The headers block is optional; without it you're on the free no-key tier.
curl -s https://stormap.ai/api/v1/tools/check_ai_crawler_access \
-H "Content-Type: application/json" \
-H "Authorization: Bearer smk_YOUR_KEY" \
-d '{"url":"https://example.com"}'
curl -s "https://stormap.ai/api/v1/guides/search?q=install+hermes"Spec: OpenAPI 3.1 · Index: /api/v1 · Site map for LLMs: /llms.txt
| Tool | What it does | Limit type |
|---|---|---|
search_guides | 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. | Guides |
get_guide | 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. | Guides |
ai_visibility_score | 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. | Analysis |
check_ai_crawler_access | 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. | Analysis |
generate_llms_txt | 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. | Analysis |
generate_ai_robots_txt | 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. | Guides |
URL tools only fetch public websites (private and internal addresses are refused), with short timeouts and size limits. 60 requests/minute burst limit. Don't use the tools to scan sites you don't own at volume.