"A server for finding information about Delphi (programming language or ancient Greek oracle site)" matching MCP tools:

• manage_accessibility_pluginA

  Orivox AI Website BuilderA

  Add (or remove) Orivox's accessibility widget: a floating accessibility button that appears on EVERY page of the site and opens a toolbar of reader aids for visitors. Reach for this the moment the user asks for an accessibility button, an accessibility menu or toolbar, or says their site should be accessible / usable with a screen reader / compliant -- this one call installs the whole thing. Do NOT hand-build an accessibility widget with apply_dom_ops. ``icon`` picks the button's glyph: "person" (default, the standard accessibility figure), "wheelchair", or "user". ``position`` puts it at the bottom "right" (default) or bottom "left" of the screen. Calling this again with different options REPLACES the existing widget instead of adding a second one, so it is also how you change the icon or move it to the other side. ``action="remove"`` takes it off the site entirely. ``changed`` is byte-honest: False means NO file was written at all, because the site already looked exactly like this -- do not announce a fresh change. True means at least one file was rewritten. ``outcome`` says which end state you are in; describe it to the user IN THEIR OWN LANGUAGE (never echo these tokens): - "installed" -- the widget is now on every page with the given icon/side. - "already_installed" -- it was already exactly like that; nothing changed. - "removed" -- it is off the site. - "was_not_installed" -- there was none, so there was nothing to remove. - "install_not_confirmed" / "removal_not_confirmed" -- the result contradicts itself. ``verify_before_reporting`` is true for these two: check the site with get_preview_url before telling the user anything about the widget, and do not claim success or failure. No re-publish is needed for a preview, but a LIVE site only shows the widget after publish_website runs again.

  ConnectorOAuth

• get_corpus_coverageA

  SRI — MCP Server InspectorA

  No arguments. Returns how many MCP servers have been read at source level, and the share of them with each category of finding (credential access, network egress, install-time execution, prompt-injection surface). Use this to judge whether checking a specific server is worth it before you look one up. It reports aggregate counts only - no per-server findings, and no verdict about any individual server.

  ConnectorNo auth

• set_slack_eventsA

  Inclusify AccessibilityA

  Decides WHICH kinds of finding get announced, once a channel is already chosen. Reach for it to quieten somewhere noisy, or to switch on something a team keeps missing. WRITES to this website's Inclusify configuration, never to the site itself, and nothing is posted to Slack by this call. Four independent switches plus a threshold, all optional: anything you leave out stays as it is. The site must already have a Slack channel — use set_slack_channel first, and this refuses until then. No confirmation is needed to turn an alert ON. Turning one OFF, or raising the score-drop threshold, means nobody hears about that class of problem any more, so those REQUIRE CONFIRMATION. Needs the PRO plan, matching the panel.

  Connector

  Destructive

  API key

• create_siteA

  sitectrlA

  Build a brand-new hosted website from a plain-language description. RETURNS IMMEDIATELY with status 'building' — the site takes about 2-3 minutes and is NOT ready when this returns. Tell the user where it will be (expected_url) and poll get_build_status with the returned claim_token. NEVER call create_site a second time for the same site: each call builds another one. Works WITHOUT signing in: an unauthenticated call builds a guest site and returns a claim_url — the user signs up free (no card) at that link to keep it; unclaimed guest sites are deleted after 72 hours. Signed in, the site lands directly on the connected account (free tier: one site, no card).

  ConnectorNo auth

• add_subdomainA

  BorealHostA

  Create and route a subdomain of a site-linked domain. Creates the DNS A record (if absent) pointing at the site's server, then configures the nginx vhost and SSL certificate on that server. The domain must already be linked to a site (see link_domain). Idempotent: if the DNS record already exists and points at the site's server, the nginx/SSL steps are (re)applied — safe to re-call, e.g. to retry SSL after DNS propagation. May take up to 3 minutes when a certificate is issued. Requires: API key with write scope. Args: domain_name: Registrable domain linked to a site (e.g. "example.com") subdomain: Subdomain label only, no dots (e.g. "blog") Returns: {"fqdn": "blog.example.com", "domain": "example.com", "site": "my-site", "message": "..."} Errors: NOT_FOUND: Domain not found VALIDATION_ERROR: Domain not linked to a site, invalid label, or an existing record points at a different server

  ConnectorNo auth

• seneschal_agent_directoryA

  Seneschal DataA

  Terse, drill-down discovery index of this ecosystem (Seneschal, FlashBank, winbit32, secresea, ZecBus, Zecmon, Ziving, Bit ID, McPai) plus a LIVE mirror of the official MCP registry (registry.modelcontextprotocol.io) — the same directory served over HTTPS at https://seneschal.space/.well-known/agent.gopher, callable here so you never leave the MCP session. Start with section="root" to see the top-level menu, then call again with section="seneschal"/"flashbank"/"winbit32"/"secresea"/"zecbus"/"zecmon"/"ziving"/"bitid"/"mcpai" to drill into a project. Each project exposes About / Agents / Actions — drill them with section="<site>/about", "<site>/agents" or "<site>/actions" (e.g. "winbit32/actions"). Seneschal additionally drills into its own services with section="seneschal/<service>" where <service> is one of private-watch, checkout, oracle, shovels, builder, data, paymaster, board, ironwood, mcp — every website + MCP capability, grouped and priced. section="registry" browses connectable third-party MCP servers (use `cursor` to page); section="about"/"agents" is the directory’s own prose. format="gopher" (default) is the compact RFC-1436 menu; format="json" returns a structured {title, items[]}. A discovery layer, not a replacement for MCP — use it to FIND tools, then connect. Free, no payment.

  ConnectorNo auth

• list_faqsA

  Gracie Barra Jiu-JitsuA

  Get all FAQ questions and answers for this site (Wix FAQ). Grouped by category. Use this to answer common questions about the site — opening hours, parking, policies, etc.

  ConnectorNo auth

• word_studyA

  bible-mcpA

  Original-language word study across the whole Bible. Query by Strong's number ('G26', 'H2617', zero-padding optional — 'H953' works), lemma (pointed or unpointed: 'חֶסֶד' or 'חסד', accented or bare Greek), Hebrew/Aramaic transliteration ('miqweh' finds מִקְוֶה, macrons optional), or English gloss ('lovingkindness'). Returns occurrence counts, gloss range, book distribution, a full scholarly lexicon entry for the top-matching word (BDB and/or Strong's for Hebrew/Aramaic, Abbott-Smith for Greek, when available — richer than the gloss, truncated to ~700 chars), and sample verses. NOTE: homographs are split by letter-suffixed Strong's variants (e.g. H4723 'hope' vs H4723a 'gathering of waters' — same written form) — when a gloss range looks too narrow for a word you suspect is richer, probe the lettered variants; the output lists every variant lemma it finds under your query. Gloss-keyed queries match substrings and may conflate lemmas — prefer Strong's or lemma queries for exact counts. language optional: grc | hbo | arc.

  ConnectorNo auth

• ask_siteA

  agentready-mcpA

  Query any website's documentation and get cited, multi-page answers in natural language. Use ask_site when you need: (1) answers that synthesize information across multiple pages of a site, (2) documentation from JS-rendered sites (React, Next.js, Vue SPAs) where web_fetch returns empty or partial HTML, (3) citations linking back to the exact source pages, (4) faster results than fetching and reading individual pages one by one. For sites not yet indexed, ask_site auto-crawls and answers in ~60s — no separate submit_site call needed.

  ConnectorNo auth

• get_articleA

  Anahana Content MCPA

  Fetch a specific Anahana article as markdown, given its full URL, site-relative path (e.g. "/en/angel-numbers/111-angel-number/"), or a bare slug from search_content results (e.g. "111-angel-number"). Tries two fetch modes against the live site in order: (1) content negotiation — GET the article URL with `Accept: text/markdown`; (2) the path-based markdown mirror at `<article-url>index.md`. Both are live. Page chrome (skip link, table of contents with dead anchors, back-to-top anchor, analytics pixel) is stripped, so what you get back is the article body. If both modes fail, returns a clear error naming the canonical HTML URL instead of silently failing. Works in all 24 languages: a full URL or a site-relative path already names its language, and a bare slug is resolved in the language given by `language` (English by default). Article slugs are identical across languages — only the title and body are translated — so the same slug plus a different `language` gives you the same article in that language.

  ConnectorNo auth

• bible_originalA

  Bibelstudium MCPA

  Return one Bible verse word-by-word in the ORIGINAL language with lemma, Strong's number and full morphology. Use this to verify what the original text says — e.g. whether a noun is singular or plural — instead of inferring it from a translation. Covers the whole Bible: the OT (book 1–39) is served from the Hebrew/Aramaic Westminster Leningrad Codex; the NT (40–66) from a Greek text type chosen via `texttyp` — "byzantine" (Majority Text, default), "sblgnt" (critical), or "tr" (Textus Receptus, the only one with the Comma Johanneum). Edition and text type are labelled in the output.

  ConnectorNo auth

• get_truss_informationA

  TrussA

  Published Truss information by topic. Localized topics (overview, about, services, engagement, fit, faq) use locale, default en; pass he for Hebrew. Language-independent topics (identity, certifications, testimonials, clients, contact) ignore locale for content selection. Prefer get_truss_overview or topic overview for broad business understanding; prefer list_truss_services for the complete service catalog.

  ConnectorNo auth

• get_shop_servicesA

  Timeplex K-Beauty BookingA

  Get the available services, prices, durations, and bookable staff or resources for a specific Korean beauty or wellness shop. Use this after finding a shop when service details, prices, durations, staff, or resources are needed before checking appointment availability. Pass lang to receive the content translated into the customer's language.

  ConnectorNo auth

• translate_codeA

  toolforteA

  Translate a piece of code from one programming language to another (for example Python to TypeScript, JavaScript to Go, VBA to Python, jQuery to plain JavaScript, SQL between dialects). Keeps the behaviour, uses the idioms of the target language, and lists what could not be translated one to one: libraries without an equivalent, integer sizes, error handling, concurrency. Meant for snippets and single files up to about 10,000 characters, not whole projects. Costs one AI generation (10 credits) with an API key; a few free demo calls per day without one. Same result as POST /api/v1/ai/code-translate.

  ConnectorNo auth

• search_datasheetsA

  sheetsdata-mcpA

  Semantic search across all extracted datasheets. Finds components matching natural language queries about specifications, features, or capabilities. Best for broad spec-based discovery across all parts (e.g. 'low-noise LDO with PSRR above 70dB'). Only searches datasheets that have been previously extracted — not all parts that exist. For finding specific parts by number, use search_parts instead.

  ConnectorNo auth

• GetBusinessDetailsA

  CodeStringers MCP ServerA

  Get business and site details for "CodeStringers Zoho Consulting Services" (https://www.codestringers.com/_api/mcp). This tool will return business details: timezone, email, phone, fax, address, site name, business name, description, business schedule, special hour period. It will also return site features that you can use via other tools (bookings, store, etc.). Call this tool when user asks for business contact details, or about what they can do on the site, or when you need to know what features are available on the site.

  ConnectorNo auth

• cloudflare_set_proxyA

  BorealHostA

  Enable or disable Cloudflare CDN proxy for a site. When enabled (orange cloud): traffic goes through Cloudflare's CDN, gets caching, DDoS protection, and SSL termination at the edge. When disabled (grey cloud): traffic goes directly to origin server. Requires: API key with write scope. Args: slug: Site identifier proxied: true to enable CDN proxy, false to disable Returns: {"domain": "my-site.borealhost.ai", "proxied": true, "ip": "1.2.3.4"}

  ConnectorNo auth

• seneschal_agent_directoryA

  SeneschalA

  Terse, drill-down discovery index of this ecosystem (Seneschal, FlashBank, winbit32, secresea, ZecBus, Zecmon, Ziving, Bit ID, McPai) plus a LIVE mirror of the official MCP registry (registry.modelcontextprotocol.io) — the same directory served over HTTPS at https://seneschal.space/.well-known/agent.gopher, callable here so you never leave the MCP session. Start with section="root" to see the top-level menu, then call again with section="seneschal"/"flashbank"/"winbit32"/"secresea"/"zecbus"/"zecmon"/"ziving"/"bitid"/"mcpai" to drill into a project. Each project exposes About / Agents / Actions — drill them with section="<site>/about", "<site>/agents" or "<site>/actions" (e.g. "winbit32/actions"). Seneschal additionally drills into its own services with section="seneschal/<service>" where <service> is one of private-watch, checkout, oracle, shovels, builder, data, paymaster, board, ironwood, mcp — every website + MCP capability, grouped and priced. section="registry" browses connectable third-party MCP servers (use `cursor` to page); section="about"/"agents" is the directory’s own prose. format="gopher" (default) is the compact RFC-1436 menu; format="json" returns a structured {title, items[]}. A discovery layer, not a replacement for MCP — use it to FIND tools, then connect. Free, no payment.

  ConnectorNo auth

• bible_concordanceA

  Bibelstudium MCPA

  Concordance / word study: find ALL occurrences of an original-language word across the Bible. Search by Strong's number (preferred; "G26" = Greek/NT, "H7225" = Hebrew/OT) or by exact lemma as returned by bible_original (e.g. "ἀγάπη", "רֵאשִׁית"). Returns total count, per-book distribution, an occurrence list with the inflected surface forms, and English lexicon data (gloss, Strong's definition; for Greek also the full Abbott-Smith entry). NT edition selectable via texttyp (default byzantine).

  ConnectorNo auth

• get_maisonA

  Origine ParisA

  Returns the Maison, Origine Paris, the Parisian fine jewellery house of recycled 18ct gold and IGI-certified lab-grown diamonds, one section at a time in the requested language. Sections: overview (identity, legal identity (SIREN), description, positioning, the by-appointment address at 21 rue de la Paix, contacts, official profiles, how orders are placed), founders (the two founders), person (one founder's full profile, biography and career with dates and references; give the name or Wikidata QID in person), entity_graph (company and founders as sourced nodes and edges), jsonld (the raw JSON-LD blocks exactly as published on the site in that language), agent_context (a short orientation for agents) and llms_txt (the site's llms.txt as published, French only). Use it for anything about the house or its founders; for the jewellery use search_catalogue. Read-only and side-effect-free: every field that can be missing carries its value, status, source URL and date; content the site does not publish in the requested language is reported as not_published and values absent from the sources as unknown, never translated or invented. Replaces get_brand_identity, get_founders, get_person_profile, get_entity_graph, get_jsonld_graph and get_llms_context.

  ConnectorNo auth

• get_product_detailA

  Origine ParisA

  Returns everything the site publishes about one piece of the Origine Paris catalogue (recycled 18ct gold, IGI-certified lab-grown diamonds), in the requested language: identity and URLs, title, the description text exactly as published (never parsed), jewellery type and published tags, collections, gold colours, the price as published on the site at the date of reading (the price payable at online checkout), variants and published sizes with the size guide, images, and the published statements on lead time, delivery, returns and care, each with its source URL and date. Give lang plus handle (or the product URL) or product_id (the Shopify gid). Use it after search_catalogue to know a piece; use get_maison for the house itself. Read-only and side-effect-free: fields the site does not publish are reported as not_published, fields this server does not relay as not_served, never invented; whether the piece can be bought online is served as the site itself publishes it, never guessed; bespoke pieces are not for sale and come with a consultation block instead. This server is read-only: it sells nothing and completes no checkout.

  ConnectorNo auth