Visdenda Free MCP
Anonymous SEO MCP: crawler directory, robots.txt, llms.txt, update radar, page scan. No API key.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"free": {
"url": "https://visdenda.com/v1/mcp/free"
}
}
}Remote endpoints
https://visdenda.com/v1/mcp/freestreamable-httpWhat it can do
Tool inventory
Tools (16)
🟢visdenda_search_ai_crawlers(query, category, provider, limit)
Search 63 AI crawlers across 22 providers by name, provider, robots token, user-agent substring, or category. Returns each crawler's canonical agent name, vendor, category, robots token, official sources and review date. Use this first when the user asks which AI bots exist, which vendor runs a bot, or what token to put in robots.txt. No network request.
Input Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"maxLength": 120,
"description": "Free-text match on provider, agent, robots token, slug or user-agent"
},
"category": {
"type": "string",
"enum": [
"answer-fetch",
"ai-search",
"training",
"search-engine",
"ads",
"unknown"
],
"description": "Optional crawler category"
},
"provider": {
"type": "string",
"minLength": 1,
"maxLength": 64,
"description": "Optional exact provider name (case-insensitive)"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 63,
"default": 20,
"description": "Max entries to return (default 20)"
}
},
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"summary": {
"type": "string"
},
"data": {
"type": "object",
"additionalProperties": true
},
"links": {
"type": "object",
"additionalProperties": {
"type": "string"
}
}
},
"required": [
"summary"
],
"additionalProperties": true
}🟢visdenda_get_ai_crawler(slug, agent, userAgent)
Read the full directory record for one crawler, selected by slug, canonical agent name, or a user-agent string. Returns vendor, category, description, robots token, user-agent needles, rDNS suffixes, published IP-range URLs, static CIDR blocks, official sources and review date. Use after search when the user needs the details or a citation. No network request.
Input Schema
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"minLength": 1,
"maxLength": 96
},
"agent": {
"type": "string",
"minLength": 1,
"maxLength": 64
},
"userAgent": {
"type": "string",
"minLength": 1,
"maxLength": 600
}
},
"additionalProperties": false,
"description": "Provide exactly one of slug, agent, or userAgent"
}Output Schema
{
"type": "object",
"properties": {
"summary": {
"type": "string"
},
"data": {
"type": "object",
"additionalProperties": true
},
"links": {
"type": "object",
"additionalProperties": {
"type": "string"
}
}
},
"required": [
"summary"
],
"additionalProperties": true
}🟢visdenda_match_user_agent(userAgent)
Given a raw user-agent or log line, return the AI/search crawlers it belongs to, ranked by exact token, prefix and substring matches. Use this when the user pastes a log entry or asks 'which bot is this?'. No network request.
Input Schema
{
"type": "object",
"properties": {
"userAgent": {
"type": "string",
"minLength": 8,
"maxLength": 600,
"description": "Raw user-agent or a log line containing one"
}
},
"required": [
"userAgent"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"summary": {
"type": "string"
},
"data": {
"type": "object",
"additionalProperties": true
},
"links": {
"type": "object",
"additionalProperties": {
"type": "string"
}
}
},
"required": [
"summary"
],
"additionalProperties": true
}🟢visdenda_check_crawler_access(url, crawlers, paths, probe, probeUserAgent)
Fetch a public URL's robots.txt once and evaluate it for specific crawlers (default: every crawler in the directory). Returns allowed/blocked per crawler, whether a matching group exists, the deciding Allow/Disallow rule, crawl-delay, and sitemap pointers. Pass paths to evaluate additional same-origin paths against the same rules (no extra request). Use when the user asks 'can GPTBot read this page?', 'is ClaudeBot blocked?', or 'which AI bots can crawl my site?'. One robots.txt request; optional probe adds one page request per path as the chosen crawler's user-agent, and probeUserAgent lets you test a specific (or forged) UA.
Input Schema
{
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Public http(s) URL; only its origin's robots.txt is read"
},
"crawlers": {
"type": "array",
"items": {
"type": "string",
"minLength": 1,
"maxLength": 64
},
"minItems": 1,
"maxItems": 20,
"description": "Optional robots tokens or agent names (default: every directory entry). Unknown names are reported as unmatched."
},
"paths": {
"type": "array",
"items": {
"type": "string",
"format": "uri"
},
"minItems": 1,
"maxItems": 4,
"description": "Optional extra paths on the same origin as url, evaluated against the same robots.txt rules (no extra request)."
},
"probe": {
"type": "boolean",
"description": "Optional. With exactly one crawler, also request the page as that crawler's user-agent to detect CDN/WAF blocks. With paths, each path is probed once."
},
"probeUserAgent": {
"type": "string",
"minLength": 8,
"maxLength": 600,
"description": "Optional custom User-Agent for the probe (requires probe=true), e.g. a forged crawler string found in logs."
}
},
"required": [
"url"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"summary": {
"type": "string"
},
"data": {
"type": "object",
"additionalProperties": true
},
"links": {
"type": "object",
"additionalProperties": {
"type": "string"
}
}
},
"required": [
"summary"
],
"additionalProperties": true
}🟢visdenda_check_llms_txt(url, includeFull)
Fetch /llms.txt for a public URL and report whether it exists, whether it returns HTML (soft 404), whether it has an H1 and valid links, and whether it follows the llmstxt.org shape. Set includeFull to also probe /llms-full.txt (status, byte size, H1, content type). Use when the user asks about llms.txt, AI-readable site maps, or agent discovery. One network request, two with includeFull.
Input Schema
{
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Public http(s) URL"
},
"includeFull": {
"type": "boolean",
"description": "Optional. Also check /llms-full.txt (adds one network request)"
}
},
"required": [
"url"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"summary": {
"type": "string"
},
"data": {
"type": "object",
"additionalProperties": true
},
"links": {
"type": "object",
"additionalProperties": {
"type": "string"
}
}
},
"required": [
"summary"
],
"additionalProperties": true
}🟢visdenda_get_radar_updates(limit, since)
Recent public P0/P1 Google Search updates with the number of public checks each one affects and a one-line public summary of the first matching check. Use this to explain why a check matters now or to connect an external Google change to a site's failures. No network request.
Input Schema
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 20,
"default": 5,
"description": "Max items to return (default 5)"
},
"since": {
"type": "string",
"format": "date",
"description": "Only updates published on or after this date (YYYY-MM-DD)"
}
},
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"summary": {
"type": "string"
},
"data": {
"type": "object",
"additionalProperties": true
},
"links": {
"type": "object",
"additionalProperties": {
"type": "string"
}
}
},
"required": [
"summary"
],
"additionalProperties": true
}🟢visdenda_check_mcp_server(url)
Inspect a public site's MCP surface: server card at /.well-known/mcp/server-cards.json, OAuth protected-resource metadata, authorization-server metadata, auth.md, and A2A agent card. Returns pass/fail per check with the fetched URL and a concrete fix. Use when the user asks whether their MCP server is discoverable, whether OAuth discovery is correct, or why a client cannot connect. Up to five probes, one network call.
Input Schema
{
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Public site origin or MCP endpoint URL; probes are built from its origin"
}
},
"required": [
"url"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"summary": {
"type": "string"
},
"data": {
"type": "object",
"additionalProperties": true
},
"links": {
"type": "object",
"additionalProperties": {
"type": "string"
}
}
},
"required": [
"summary"
],
"additionalProperties": true
}🟢visdenda_check_agent_readiness(url, checks)
Run up to eight agent-readiness probes against a public site (default: robots, sitemap, llms.txt, content signals, markdown negotiation, API catalog, auth.md, MCP server card). Returns a 0–100 score, pass/fail/warn/na counts and per-check detail. Use when the user asks 'is my site ready for AI agents?' or wants a prioritized agent-readiness audit. One network call; each probe may fetch one to three URLs.
Input Schema
{
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Public site origin or page URL"
},
"checks": {
"type": "array",
"items": {
"type": "string",
"enum": [
"robots-txt",
"sitemap",
"content-signals",
"llms-txt",
"markdown-negotiation",
"link-discovery",
"api-catalog",
"auth-md",
"oauth-discovery",
"oauth-protected-resource",
"a2a-agent-card",
"mcp-server-card",
"web-bot-auth",
"dns-aid",
"skills-index",
"acp",
"ap2",
"mpp",
"ucp",
"x402"
]
},
"minItems": 1,
"maxItems": 8,
"description": "Optional subset of probe ids (default: the eight cheap probes)"
}
},
"required": [
"url"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"summary": {
"type": "string"
},
"data": {
"type": "object",
"additionalProperties": true
},
"links": {
"type": "object",
"additionalProperties": {
"type": "string"
}
}
},
"required": [
"summary"
],
"additionalProperties": true
}🟢visdenda_scan_page(url, updateId)
Run the same deterministic single-page scan as the public free tool (20+ checks: meta, canonical, robots, sitemap, llms.txt, schema, hreflang, redirects and agent-readiness basics). Pass updateId to attach an update's public checks and mark which affected checks the scan covers. Returns a grade, pass/fail counts, top issues, every failing and warning finding with details (findings), the attached update and a shareable report URL valid for seven days. Use when the user wants a broad one-page audit rather than a single check. One network call and one scan from the shared daily 3/day/IP scan quota.
Input Schema
{
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Public http(s) URL"
},
"updateId": {
"type": "string",
"minLength": 1,
"maxLength": 120,
"description": "Optional public radar update id or slug to attach its public checks"
}
},
"required": [
"url"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"summary": {
"type": "string"
},
"data": {
"type": "object",
"additionalProperties": true
},
"links": {
"type": "object",
"additionalProperties": {
"type": "string"
}
}
},
"required": [
"summary"
],
"additionalProperties": true
}🟢visdenda_connect_account(email, scopes)
Start a self-service agent registration: given the user's email and optional scopes, return a claim URL, a six-digit code and a claim token. The user opens the URL, signs in and approves scopes; the agent then polls /v1/oauth2/token with the claim token to receive a one-hour access token for the account MCP server. Use only when the user explicitly wants to keep results, monitor a site, or read Search Console data. Creates a pending registration, no site changes.
Input Schema
{
"type": "object",
"properties": {
"email": {
"type": "string",
"format": "email",
"description": "The account owner's email (must match the account they sign in with)"
},
"scopes": {
"type": "array",
"items": {
"type": "string",
"enum": [
"radar:read",
"rules:read",
"audit:read",
"sites:write"
]
},
"minItems": 1,
"maxItems": 4,
"description": "Requested scopes (default: audit:read)"
}
},
"required": [
"email"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"summary": {
"type": "string"
},
"data": {
"type": "object",
"additionalProperties": true
},
"links": {
"type": "object",
"additionalProperties": {
"type": "string"
}
}
},
"required": [
"summary"
],
"additionalProperties": true
}🟢visdenda_check_sitemap(url)
Fetch a site's sitemap and validate its XML structure, entry counts, the 50,000-URL per-file limit and sitemap-index children. If the URL is a normal page, /sitemap.xml on its origin is checked instead; a URL ending in .xml or .xml.gz is used as-is. Returns pass/fail/na with details and Google's official source. One request, plus up to ten for sitemap-index children.
Input Schema
{
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Public site/page URL, or the sitemap URL itself (.xml/.xml.gz)"
}
},
"required": [
"url"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"summary": {
"type": "string"
},
"data": {
"type": "object",
"additionalProperties": true
},
"links": {
"type": "object",
"additionalProperties": {
"type": "string"
}
}
},
"required": [
"summary"
],
"additionalProperties": true
}🟢visdenda_check_robots_txt(url)
Fetch /robots.txt for a public URL, validate its directives and check that declared Sitemap pointers resolve. Returns pass/fail/na with details and the official source. Use when the user asks whether robots.txt is valid or whether its sitemaps are reachable. One request, plus up to three sitemap-pointer probes.
Input Schema
{
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Public http(s) URL; its origin's robots.txt is read"
}
},
"required": [
"url"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"summary": {
"type": "string"
},
"data": {
"type": "object",
"additionalProperties": true
},
"links": {
"type": "object",
"additionalProperties": {
"type": "string"
}
}
},
"required": [
"summary"
],
"additionalProperties": true
}🟢visdenda_check_page_signals(url, checks)
Run a focused subset of the public single-page checks for one URL: canonical tag, noindex, meta preview, hreflang and structured data (JSON-LD). Returns one verdict per selected signal with summary and details. Use when the user asks about canonicalization, accidental noindex, title/meta length, hreflang or schema markup. One network request; does not create a report or consume the scan quota.
Input Schema
{
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Public http(s) URL"
},
"checks": {
"type": "array",
"items": {
"type": "string",
"enum": [
"canonical",
"noindex",
"meta",
"hreflang",
"structured-data"
]
},
"minItems": 1,
"maxItems": 5,
"description": "Optional subset of signals (default: all five)"
}
},
"required": [
"url"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"summary": {
"type": "string"
},
"data": {
"type": "object",
"additionalProperties": true
},
"links": {
"type": "object",
"additionalProperties": {
"type": "string"
}
}
},
"required": [
"summary"
],
"additionalProperties": true
}🟢visdenda_get_radar_update(id)
Read one public P0/P1 radar update by id or public slug: summary, official links, the public checks it affects and the latest per-check verdicts. Use after visdenda_get_radar_updates when the user asks what a specific Google update means or which checks it touches. No network request.
Input Schema
{
"type": "object",
"properties": {
"id": {
"type": "string",
"minLength": 1,
"maxLength": 160,
"description": "Radar update id or public slug"
}
},
"required": [
"id"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"summary": {
"type": "string"
},
"data": {
"type": "object",
"additionalProperties": true
},
"links": {
"type": "object",
"additionalProperties": {
"type": "string"
}
}
},
"required": [
"summary"
],
"additionalProperties": true
}🟢visdenda_explain_rule(id)
Explain one public Visdenda check by id: public title and summary, severity, requirement level, what it applies to, site types, page roles and the official Google documentation it comes from. Use when the user asks what a check verifies or why it matters. No network request.
Input Schema
{
"type": "object",
"properties": {
"id": {
"type": "string",
"minLength": 1,
"maxLength": 160,
"description": "Public rule id (see visdenda_get_radar_update or visdenda_get_radar_updates)"
}
},
"required": [
"id"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"summary": {
"type": "string"
},
"data": {
"type": "object",
"additionalProperties": true
},
"links": {
"type": "object",
"additionalProperties": {
"type": "string"
}
}
},
"required": [
"summary"
],
"additionalProperties": true
}🟢visdenda_verify_crawler_ip(ip, agent)
Check whether an IP belongs to a named AI crawler. Pass agent (slug, agent name or robots token) to test that crawler's official ranges; omit it to try static CIDR blocks first, then reverse DNS and the crawlers whose rDNS suffixes match. Returns matched/mismatch/unavailable/not-checked plus the CIDR and rDNS evidence. Use when the user pastes a log entry and asks whether the bot is genuine. One network call; fails soft on DNS/range errors.
Input Schema
{
"type": "object",
"properties": {
"ip": {
"type": "string",
"minLength": 3,
"maxLength": 64,
"description": "IPv4 or IPv6 address"
},
"agent": {
"type": "string",
"minLength": 1,
"maxLength": 96,
"description": "Optional crawler slug, agent name or robots token"
}
},
"required": [
"ip"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"summary": {
"type": "string"
},
"data": {
"type": "object",
"additionalProperties": true
},
"links": {
"type": "object",
"additionalProperties": {
"type": "string"
}
}
},
"required": [
"summary"
],
"additionalProperties": true
}Community
Evidence