Visdenda Free MCP server
com.visdenda/freevisdenda.comstreamable-httpv0.1.2Scanned
Anonymous SEO MCP: crawler directory, robots.txt, llms.txt, update radar, page scan. No API key.
10 tools: 4 change things and 6 only read.
- Reads private data · 2
- Reads text others write · 5
- Can send data out · 5
- 2 findings
Tools listed without sign-in. Remote posture
With Anlyon
4 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Visdenda Free MCP server can do
The Visdenda Free MCP server is published by visdenda.com, a domain the MCP Registry verified. It has 10 tools. It can create or change data (4 tools: visdenda_match_user_agent, visdenda_check_agent_readiness, visdenda_scan_page and visdenda_connect_account), but cannot delete data. 6 tools only read.
2 tools read private data (visdenda_get_ai_crawler and visdenda_check_crawler_access); 5 tools bring in text other people can write (visdenda_check_crawler_access, visdenda_check_llms_txt, visdenda_check_mcp_server and 2 more); 5 tools can send data out of your system (visdenda_check_crawler_access, visdenda_check_llms_txt, visdenda_check_mcp_server and 2 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 2 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 18, 2026, version 0.1.2.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
10 tools
Changes things 4Claude Code: ask
visdenda_check_agent_readinessRun 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).Reads text others writeCan send data out1 finding
Why it is in this group
- The description's first verb is "run": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "visdenda_check_agent_readiness" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "run": a word for a change.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
- idempotentHint: true
visdenda_connect_accountStart 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.No findings
Why it is in this group
- The description's first verb is "start": a word for a change.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
- idempotentHint: false
visdenda_match_user_agentGiven a raw user-agent or log line, return the AI/search crawlers it belongs to, ranked by exact token, prefix and substring matches.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
visdenda_scan_pageRun 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)…Reads text others writeCan send data out1 finding
Why it is in this group
- The description's first verb is "run": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "visdenda_scan_page" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "run": a word for a change.
Description, as the server wrote it 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). Returns a grade, pass/fail counts, top issues 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 anonymous scan from the daily scan quota.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
- idempotentHint: true
Only reads 6Show 6 read-only tools
visdenda_check_crawler_accessFetch a public URL's robots.txt once and evaluate it for specific crawlers (default: every crawler in the directory).Reads private dataReads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "fetch": a word for reading.
What it can reach
- private-dataThe description's first sentence says "fetch" and "directory": it reads files.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "fetch" and "url": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it 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. 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 as the chosen crawler's user-agent.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
- idempotentHint: true
visdenda_check_llms_txtFetch /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 shap…Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "fetch": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "fetch" and "url": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it 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. Use when the user asks about llms.txt, AI-readable site maps, or agent discovery. One network request.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
- idempotentHint: true
visdenda_check_mcp_serverInspect 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 car…Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "inspect": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
- idempotentHint: true
visdenda_get_ai_crawlerRead the full directory record for one crawler, selected by slug, canonical agent name, or a user-agent string.Reads private dataNo findings
Why it is in this group
- The name "visdenda_get_ai_crawler" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "read" and "directory": it reads files.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
visdenda_get_radar_updatesRecent P0/P1 Google Search updates with the number of active audit rules each one affects.No findings
Why it is in this group
- The name "visdenda_get_radar_updates" says "get": a word for reading.
Description, as the server wrote it Recent P0/P1 Google Search updates with the number of active audit rules each one affects. Use this to explain why a rule matters now or to connect an external Google change to a site's failures. No network request.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
visdenda_search_ai_crawlersSearch 63 AI crawlers across 22 providers by name, provider, robots token, user-agent substring, or category.No findings
Why it is in this group
- The name "visdenda_search_ai_crawlers" says "search": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
50 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 2 private-data tools breaks every one.
- Reads private data2
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write5
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out5
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__free__visdenda_check_crawler_access",
"mcp__free__visdenda_get_ai_crawler"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 18, 2026, 16:19 UTC, unchanged since Nov 18, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 4
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://visdenda.com/.well-known/oauth-protected-resource
- Authorization servers
- https://visdenda.com/v1/oauth
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://visdenda.com/v1/mcp/free: tools/list returned 10 tools to an anonymous client, including visdenda_match_user_agent (write), visdenda_check_agent_readiness (write), visdenda_scan_page (write), visdenda_connect_account (write)
Findings
Matches of fixed checks, with the text they matched.
The server marks "visdenda_check_agent_readiness" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "run": a word for a change.
The server marks "visdenda_scan_page" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "run": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.1.2. Values in angle brackets are yours to fill in.
claude mcp add --transport http free https://visdenda.com/v1/mcp/freeclaude mcp add --transport http free https://visdenda.com/v1/mcp/freeRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__free__visdenda_search_ai_crawlers",
"mcp__free__visdenda_get_ai_crawler",
"mcp__free__visdenda_get_radar_updates"
],
"ask": [
"mcp__free__visdenda_match_user_agent",
"mcp__free__visdenda_check_crawler_access",
"mcp__free__visdenda_check_llms_txt",
"mcp__free__visdenda_check_mcp_server",
"mcp__free__visdenda_check_agent_readiness",
"mcp__free__visdenda_scan_page",
"mcp__free__visdenda_connect_account"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as free. Review it before you use it.
Capability tags behind 6 rules
- mcp__free__visdenda_get_ai_crawler private-data
- mcp__free__visdenda_check_crawler_access private-data, untrusted-input, outbound
- mcp__free__visdenda_check_llms_txt untrusted-input, outbound
- mcp__free__visdenda_check_mcp_server untrusted-input, outbound
- mcp__free__visdenda_check_agent_readiness untrusted-input, outbound
- mcp__free__visdenda_scan_page untrusted-input, outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.visdenda/free/verify?hash=8bdbb80bf6ce9d02ce874f56f235d781a124c4c2f182d4183e4c7c01626f7e80" | jq -e '.changed == false'Pinned hash 8bdbb80bf6ce, from Nov 18, 2026, 05:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.visdenda/free/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.visdenda/free)Source: MCP Registry · repository. Synced Nov 18, 2026, 05:17 UTC.
Visdenda Free MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Visdenda Free MCP server safe?
- No scan can promise that. What its definitions show: 10 tools, 4 of which can change, send or delete something, and 2 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Visdenda Free MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Visdenda Free MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Visdenda Free MCP server have?
- 10 tools: 4 write, 6 read. visdenda_match_user_agent, visdenda_check_agent_readiness, visdenda_scan_page, visdenda_connect_account, visdenda_search_ai_crawlers, visdenda_get_ai_crawler, visdenda_check_crawler_access, visdenda_check_llms_txt and 2 more.
Does the Visdenda Free MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Visdenda Free MCP server send data to outside services?
- 5 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): visdenda_check_crawler_access, visdenda_check_llms_txt, visdenda_check_mcp_server, visdenda_check_agent_readiness and visdenda_scan_page.
Has the Visdenda Free MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 18, 2026.