# org.directindex/scanner (remote · directindex.org) AI-agent readiness of business websites: scans, city indexes, assistants' answers, direct links. - Trust score: 64/100 (medium) - Registry status: active - Liveness: live - Owner verified: no - Last scored: 2026-10-17 ## Components - remote · `directindex.org`: 64/100 (this document), [markdown](https://verifymcp.io/servers/org-directindex-scanner/directindex.md), [page](https://verifymcp.io/servers/org-directindex-scanner/directindex) ## Channel facts - Endpoint: `https://directindex.org/mcp` - Transports: `streamable-http` - Auth: `none` - Version: `0.3.0` ## Trust breakdown How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog) Scored 2026-10-17. - **Endpoint Security**: 66/100 - The endpoint's TLS certificate is valid, in date, and uses a strong key. - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one. - HTTPS check failed: the endpoint is reachable over plaintext HTTP. - HSTS check failed: the Strict-Transport-Security header is absent. - DNSSEC is configured correctly; the domain's records validate against the full chain to the root. - **Transport & Reachability**: 100/100 - Verified streamable-http transport via a live MCP handshake. - **Schema Quality & AI Usability**: 56/100 - AI-judged instruction clarity (excellent). - Context-footprint check failed: tool/resource definitions use about 7711 tokens (~428/item across 18 items; 18 tools + 0 resources), over budget; trim descriptions and params. - Usage-examples check failed: none of the tools include examples. - **Stability & Change Management**: 0/100 - Stability check failed: schema churn in the 3 days we've observed: 0 tool removals, 4 breaking changes, 0 auth/transport breaks, 14 additions. - **Tool Coverage**: 98/100 - 100% of tools have a non-trivial description (not blank, and not just the tool's name). - 94% of tool parameters carry a description. - **Tool Safety**: 100/100 - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured. - We read all 18 captured tool definition(s), and no name or description among them implies an irreversible operation. - An AI judge read all 19 captured unit(s) of tool text and found none that tries to manipulate the model reading it. - **Capabilities**: 100/100 - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28. ## Install ### How do I install the org.directindex/scanner MCP server? org.directindex/scanner is a hosted endpoint at https://directindex.org/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation. ### Claude ```bash claude mcp add --transport http org-directindex-scanner 'https://directindex.org/mcp' ``` ### Cursor ```json { "mcpServers": { "org-directindex-scanner": { "url": "https://directindex.org/mcp" } } } ``` ### VS Code ```json { "servers": { "org-directindex-scanner": { "type": "http", "url": "https://directindex.org/mcp" } } } ``` ### Codex ```toml [mcp_servers.org-directindex-scanner] url = "https://directindex.org/mcp" ``` ### opencode ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "org-directindex-scanner": { "type": "remote", "url": "https://directindex.org/mcp", "enabled": true } } } ``` ### OpenClaw ```bash openclaw mcp add org-directindex-scanner --url 'https://directindex.org/mcp' --transport streamable-http ``` ### Hermes ```yaml mcp_servers: org-directindex-scanner: url: "https://directindex.org/mcp" ``` ### Netclaw ```json { "McpServers": { "org-directindex-scanner": { "Transport": "http", "Url": "https://directindex.org/mcp" } } } ``` ### Vellum ```bash assistant mcp add org-directindex-scanner -t streamable-http -u 'https://directindex.org/mcp' ``` ### Other ```json { "mcpServers": { "org-directindex-scanner": { "type": "http", "url": "https://directindex.org/mcp" } } } ``` The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs. ## Changelog Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims. ### 2026-10-17 (score 64, −3) - [security regression] Stability: 0.07 → fail - [security regression] A breaking change shipped without a version bump: still 0.2.0 - [functional regression] Schema quality: 139 → 428 - [functional regression] “assistant_destinations” added a required parameter “context”, so existing callers break - [functional regression] “assistant_destinations” added a required parameter “llm_model”, so existing callers break - [functional regression] “assistant_recommendations” added a required parameter “context”, so existing callers break - [functional regression] “assistant_recommendations” added a required parameter “llm_model”, so existing callers break - [functional regression] “city_changes” added a required parameter “context”, so existing callers break - [functional regression] “city_changes” added a required parameter “llm_model”, so existing callers break - [functional regression] “city_leaderboard” added a required parameter “context”, so existing callers break - [functional regression] “city_leaderboard” added a required parameter “llm_model”, so existing callers break - [functional regression] “compare_cities” added a required parameter “context”, so existing callers break - [functional regression] “compare_cities” added a required parameter “llm_model”, so existing callers break - [functional regression] “country_summary” added a required parameter “context”, so existing callers break - [functional regression] “country_summary” added a required parameter “llm_model”, so existing callers break - [functional regression] “direct_record” added a required parameter “context”, so existing callers break - [functional regression] “direct_record” added a required parameter “llm_model”, so existing callers break - [functional regression] “find_direct_places” added a required parameter “context”, so existing callers break - [functional regression] “find_direct_places” added a required parameter “llm_model”, so existing callers break - [functional regression] “get_deep_report” added a required parameter “context”, so existing callers break - [functional regression] “get_deep_report” added a required parameter “llm_model”, so existing callers break - [functional regression] “get_site_report” added a required parameter “context”, so existing callers break - [functional regression] “get_site_report” added a required parameter “llm_model”, so existing callers break - [functional regression] “list_cities” added a required parameter “context”, so existing callers break - [functional regression] “list_cities” added a required parameter “llm_model”, so existing callers break - [functional regression] “order_deep_report” added a required parameter “context”, so existing callers break - [functional regression] “order_deep_report” added a required parameter “llm_model”, so existing callers break - [functional regression] “rankings” added a required parameter “context”, so existing callers break - [functional regression] “rankings” added a required parameter “llm_model”, so existing callers break - [functional regression] “scan_website” added a required parameter “context”, so existing callers break - [functional regression] “scan_website” added a required parameter “llm_model”, so existing callers break - [functional regression] “search_places” added a required parameter “context”, so existing callers break - [functional regression] “search_places” added a required parameter “llm_model”, so existing callers break - [functional regression] “vendor_report” added a required parameter “context”, so existing callers break - [functional regression] “vendor_report” added a required parameter “llm_model”, so existing callers break - [functional regression] “vendor_terms” added a required parameter “context”, so existing callers break - [functional regression] “vendor_terms” added a required parameter “llm_model”, so existing callers break - [functional regression] “what_assistants_say” added a required parameter “context”, so existing callers break - [functional regression] “what_assistants_say” added a required parameter “llm_model”, so existing callers break - [functional improvement] Tool coverage: 85% → 94% - [functional] Schema quality: good → excellent - [cosmetic] “assistant_destinations” added an optional parameter “conversation_id” - [cosmetic] “assistant_recommendations” added an optional parameter “conversation_id” - [cosmetic] “city_changes” added an optional parameter “conversation_id” - [cosmetic] “city_leaderboard” added an optional parameter “conversation_id” - [cosmetic] “compare_cities” added an optional parameter “conversation_id” - [cosmetic] “country_summary” added an optional parameter “conversation_id” - [cosmetic] “direct_record” added an optional parameter “conversation_id” - [cosmetic] “find_direct_places” added an optional parameter “conversation_id” - [cosmetic] “get_deep_report” added an optional parameter “conversation_id” - [cosmetic] “get_site_report” added an optional parameter “conversation_id” - [cosmetic] “list_cities” added an optional parameter “conversation_id” - [cosmetic] “order_deep_report” added an optional parameter “conversation_id” - [cosmetic] “rankings” added an optional parameter “conversation_id” - [cosmetic] “scan_website” added an optional parameter “conversation_id” - [cosmetic] “search_places” added an optional parameter “conversation_id” - [cosmetic] “vendor_report” added an optional parameter “conversation_id” - [cosmetic] “vendor_terms” added an optional parameter “conversation_id” - [cosmetic] “what_assistants_say” added an optional parameter “conversation_id” ### 2026-10-16 (score 67, +1) - [security] Tool “order_deep_report” rewrote its description, which is the text the model reads ### 2026-10-15 (score 66, +6) - [security improvement] Authorization: unverified → partial - [security] The server rewrote its instructions, which are the text every model session reads - [functional regression] Schema quality: pass → fail - [functional improvement] Tool coverage: 75% → 85% - [functional improvement] Stability: unverified → 0.03 - [functional] New tool “assistant_destinations” - [functional] New tool “assistant_recommendations” - [functional] New tool “city_changes” - [functional] New tool “compare_cities” - [functional] New tool “country_summary” - [functional] New tool “direct_record” - [functional] New tool “find_direct_places” - [functional] New tool “get_deep_report” - [functional] New tool “order_deep_report” - [functional] New tool “rankings” - [functional] New tool “search_places” - [functional] New tool “vendor_report” - [functional] New tool “vendor_terms” - [functional] New tool “what_assistants_say” - [cosmetic] Tool “city_leaderboard” changed its title: City leaderboard - [cosmetic] Tool “get_site_report” changed its title: Get site report - [cosmetic] Tool “list_cities” changed its title: List cities - [cosmetic] Tool “scan_website” changed its title: Scan website ### 2026-10-14 (score 60) First indexed and scored. ## MCP tools (18) ### `scan_website` (~359 tokens) Scan website Scan a business website and return its Agent-Direct Score (0 to 100), grade, findings and fixes. Reuses a scan under 24 hours old; otherwise runs one, which takes 10 to 40 seconds. Input parameters: - `context` (string, required): Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include,… - `conversation_id` (string): Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Kee… - `llm_model` (string, required): The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model… - `url` (string, required): Website address, for example yourbusiness.com ### `get_site_report` (~341 tokens) Get site report Return the latest Agent-Direct report for a domain that has already been scanned, including findings, fixes and agent-discoverability checks. Input parameters: - `context` (string, required): Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include,… - `conversation_id` (string): Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Kee… - `domain` (string, required): Registered domain, for example belcanto.pt - `llm_model` (string, required): The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model… ### `city_leaderboard` (~348 tokens) City leaderboard Businesses in a city index ranked by Agent-Direct Score, with grade, menu format, direct channel and whether AI crawlers are blocked. Input parameters: - `city` (string, required): City slug, for example lisbon - `context` (string, required): Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include,… - `conversation_id` (string): Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Kee… - `limit` (integer) - `llm_model` (string, required): The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model… ### `find_direct_places` (~742 tokens) Find direct places Places in a city that take a booking or an order on their own website, best Agent-Direct Scores first, with the direct booking or ordering link for each (the owner's corrected link where the business is claimed), the vendor behind it, verified_at when a browser reached the step before confirming, the vendor's terms for agents when noted, the hours, and follow links (https://directindex.org/go/{domain}/book, /order, /menu) that count. Use it to recommend places a person can book or order from directly, without a marketplace. Optional query: a cuisine, a dish or a few words, for example pizza, sushi, vegan, francesinha. Optional filters: lat, lon and radius_m for places near a point; open_now for places open at this moment in the city's zone (unknown hours stay in, marked null); verified_only for links a browser verified; vendor for one booking or ordering vendor (slug as on https://directindex.org/vendors). The same lists exist as pages at https://directindex.org/city/{slug}/direct, /direct/book, /direct/order and /direct/{want}; the full record of one place is available by domain. Input parameters: - `city` (string, required): City slug, for example lisbon; see list_cities - `context` (string, required): Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include,… - `conversation_id` (string): Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Kee… - `lat` (number): Latitude of the person; with lon, only places within radius_m - `limit` (integer) - `llm_model` (string, required): The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model… - `lon` (number): Longitude of the person - `open_now` (boolean): Only places open right now by their OpenStreetMap hours, in the city's zone; places with unreadable hours stay in with open_now null - `query` (string): What the person wants: a cuisine, a dish or a few words. Empty for any. - `radius_m` (integer): Metres around lat, lon - `vendor` (string): Only places on this booking or ordering vendor, by slug: zenchef, sevenrooms, toast ... - `verified_only` (boolean): Only links a browser verified: an agent reached the step before confirming - `want` (string): book: a table; order: food to collect or deliver; any: either ### `list_cities` (~310 tokens) List cities List the city indexes that exist, with counts and status. Input parameters: - `context` (string, required): Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include,… - `conversation_id` (string): Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Kee… - `llm_model` (string, required): The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model… ### `order_deep_report` (~502 tokens) Order deep report Order the paid deep report (5 EUR, one-off) for a business in a city index: ChatGPT, Claude and Gemini are asked ten questions about it the way people ask, every answer is kept in full with where it sent people, plus the nearest similar places, the fix plan with the kit to paste, what an agent reads on the site, a page and a PDF. Returns the order token and a Stripe checkout link for the person to pay (nothing is charged until they do); the report is written in about fifteen minutes after payment and also emailed, and its status and text can be read by the token. Input parameters: - `context` (string, required): Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include,… - `conversation_id` (string): Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Kee… - `domain` (string, required): The business's registered domain, for example belcanto.pt; it must be in a city index (see city_leaderboard) - `email` (string, required): Where the report and the receipt go - `lang` (string): Language of the delivery mail: en, pt, es, fr, de, nl, it, da or cs - `llm_model` (string, required): The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model… ### `get_deep_report` (~364 tokens) Get deep report Status of a deep report order by its token, and the finished report itself as Markdown once it is done (every answer in full, the table of where answers sent people, the nearest similar places, the fix plan and the kit). Input parameters: - `context` (string, required): Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include,… - `conversation_id` (string): Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Kee… - `llm_model` (string, required): The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model… - `order` (string, required): The 32-character order token from order_deep_report ### `what_assistants_say` (~409 tokens) What assistants say What ChatGPT, Claude and Gemini answer about one business: the latest verdict per question (official website, where to book, where to order: own site, vendor, marketplace, directory, no link), the answers quoted, the questions people ask for which the business was named, and one sentence on why an assistant sent people elsewhere. For businesses in a city index that have been asked about; see the report at https://directindex.org/r/{domain}. Input parameters: - `context` (string, required): Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include,… - `conversation_id` (string): Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Kee… - `domain` (string, required): Registered domain, for example belcanto.pt - `llm_model` (string, required): The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model… ### `assistant_recommendations` (~436 tokens) Assistant recommendations The places ChatGPT, Claude and Gemini name in a city when asked the way people ask ('best pizza delivered right now', 'book me a table for Saturday'): per question, the places named, which assistant named each, whether with a link to the place's own site, and the direct booking or ordering link where the place has one. Pages: https://directindex.org/city/{slug}/recommended and /recommended/{question}. Input parameters: - `city` (string, required): City slug, for example lisbon; see list_cities - `context` (string, required): Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include,… - `conversation_id` (string): Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Kee… - `intent` (string): A question key to narrow to one question, for example pizza-delivery, romantic, fado; empty for all - `llm_model` (string, required): The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model… ### `assistant_destinations` (~420 tokens) Assistant destinations Where the assistants send people in a city: the league table of destinations (the businesses' own sites, each marketplace and directory by name, press and guides, other sites) with the share of answers that link each one, per assistant and overall, and the headline shares (direct, marketplace, the top marketplace). Pages: https://directindex.org/city/{slug}/assistants and https://directindex.org/assistants for every city. Input parameters: - `city` (string, required): City slug, for example lisbon; 'all' for every city together - `context` (string, required): Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include,… - `conversation_id` (string): Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Kee… - `limit` (integer): How many destinations - `llm_model` (string, required): The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model… ### `compare_cities` (~448 tokens) Compare cities Two city indexes side by side: business websites scanned, the share that take a booking or an order on their own site, the share that turn an AI crawler away, the share scoring A or B, grades, menus, channels, builders, vendors, the assistants' direct share where probed, and the month-by-month numbers. Takes index slugs or city names (lisbon, Porto, berlin-cafes-bars). Page: https://directindex.org/compare/{a}/{b}. Input parameters: - `a` (string, required): First city or index slug, for example lisbon - `b` (string, required): Second city or index slug, for example porto - `context` (string, required): Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include,… - `conversation_id` (string): Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Kee… - `kind` (string): Which kind of index when a city name is given - `llm_model` (string, required): The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model… ### `country_summary` (~392 tokens) Country summary A country's indexes added together (ISO code, for example PT or DE): sites scanned, direct share, crawler-blocked share, A-or-B share, the cities with their numbers, the kinds, the vendors common in the country. Without a code: every country with an index. Pages: https://directindex.org/country/{code} and /countries. Input parameters: - `code` (string): Two-letter country code, for example PT; empty for the list of countries - `context` (string, required): Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include,… - `conversation_id` (string): Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Kee… - `llm_model` (string, required): The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model… ### `rankings` (~400 tokens) Rankings Every city index of a kind ranked on three measures with its sample size and date: direct share (a booking or ordering path on the business's own domain), crawler-open share (not turned away at the edge) and A-or-B share. Indexes with fewer than 100 scanned sites are listed unranked. Page: https://directindex.org/rankings?kind=. Input parameters: - `context` (string, required): Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include,… - `conversation_id` (string): Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Kee… - `kind` (string): restaurants, cafes, salons, clinics, tours, or all (whole cities, every kind added) - `llm_model` (string, required): The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model… ### `search_places` (~515 tokens) Search places Find businesses in the city indexes by name or domain, filtered by city, kind, grade, builder, booking or ordering vendor and finding (for example menu_pdf, edge_blocks, no_structured, booking_marketplace). Fifty results a page, best Agent-Direct Scores first, each with its report link. Free, no contacts. Page: https://directindex.org/search. Input parameters: - `builder` (string): Builder slug, for example wordpress, wix, squarespace - `city` (string): City or index slug, for example berlin or berlin-cafes-bars - `context` (string, required): Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include,… - `conversation_id` (string): Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Kee… - `finding` (string): Finding id, for example menu_pdf, edge_blocks, robots_blocks, no_structured, no_text_nojs, no_channel, booking_marketplace, ordering_marketplace, no_llms_txt - `grade` (string) - `kind` (string) - `llm_model` (string, required): The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model… - `page` (integer) - `q` (string): A name, part of a name, or a domain - `vendor` (string): Vendor slug, for example thefork, zenchef, toast ### `direct_record` (~429 tokens) Direct record The direct record of a business: the booking, ordering and menu links an agent should use instead of a marketplace, where each leads (the business's own site or a named vendor), whether and when a browser verified it, the hours (OpenStreetMap form and schema.org, with open_now), phone, address, the assistants' latest verdicts, how often agents read and followed it this month, the score, and the source and date of every fact. Corrected by the owner where the business is claimed. Also GET https://directindex.org/api/direct/{domain}. Input parameters: - `context` (string, required): Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include,… - `conversation_id` (string): Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Kee… - `domain` (string, required): Registered domain, for example belcanto.pt - `llm_model` (string, required): The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model… ### `vendor_report` (~400 tokens) Vendor report A booking or ordering vendor across the index: software on the vendor's domain or a marketplace, booking or ordering, how many sites use it, their average score and A or B share, how the browser action test went on them, the cities, example sites, and the vendor's terms for agents when a note exists. Vendor slugs as on https://directindex.org/vendors (zenchef, sevenrooms, thefork, toast ...). Input parameters: - `context` (string, required): Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include,… - `conversation_id` (string): Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Kee… - `llm_model` (string, required): The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model… - `slug` (string, required): Vendor slug, for example zenchef ### `city_changes` (~420 tokens) City changes What changed in a city index over the last days: findings fixed or new, grades up or down, AI crawlers turned away or let in, direct booking or ordering channels and vendors gained or lost, and assistants that changed their answer about a business. Each change links the business's report. Also a page (https://directindex.org/city/{slug}/changes), an Atom feed (/changes.xml) and JSON (/api/city/{slug}/changes?days=30). Input parameters: - `city` (string, required): City slug, for example lisbon; see list_cities - `context` (string, required): Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include,… - `conversation_id` (string): Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Kee… - `days` (integer) - `llm_model` (string, required): The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model… ### `vendor_terms` (~391 tokens) Vendor terms Whether a booking or ordering vendor's terms let an AI agent book or order through it: allowed, partners only, banned, or not stated; with the vendor's own page and the date the terms were read. Without a vendor: every researched vendor. Use it before sending a person to book or order through a vendor on an agent's behalf. Input parameters: - `context` (string, required): Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include,… - `conversation_id` (string): Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Kee… - `llm_model` (string, required): The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model… - `vendor` (string): Vendor slug as it appears in reports, for example thefork, opentable, square ## Diagnostics Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/org-directindex-scanner/directindex#diagnostics ## Score history - 2026-10-17: 64 - 2026-10-16: 67 - 2026-10-15: 66 - 2026-10-14: 60 ## Common questions ### What is the org.directindex/scanner MCP server? org.directindex/scanner is an MCP server listed in the public MCP registry as org.directindex/scanner. AI-agent readiness of business websites: scans, city indexes, assistants' answers, direct links. This page covers its hosted endpoint (https://directindex.org/mcp). ### Is the org.directindex/scanner MCP server safe to use? org.directindex/scanner scores 64 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm. ### What tools does the org.directindex/scanner MCP server expose? org.directindex/scanner exposes 18 tools: scan_website, get_site_report, city_leaderboard, find_direct_places, list_cities, and 13 more. Their descriptions and schemas cost roughly 7,626 tokens of context every time the server is loaded. ### Does the org.directindex/scanner MCP server require authentication? No. We connected to org.directindex/scanner without credentials and it answered, so anything it exposes is reachable by anyone who knows the address. ### Is the org.directindex/scanner MCP server still maintained? org.directindex/scanner is still listed as active in the MCP registry. We last reached this channel on 17 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced. ## Links - Remote endpoint: https://directindex.org/mcp - Website: https://directindex.org/ - Changelog RSS feed: https://verifymcp.io/servers/org-directindex-scanner/directindex.xml - Changelog JSON feed: https://verifymcp.io/servers/org-directindex-scanner/directindex.json - HTML version of this page: https://verifymcp.io/servers/org-directindex-scanner/directindex