Assemble a complete RAG (Retrieval-Augmented Generation) prompt from retrieved context chunks and a user query. Handles token budgeting, citation numbering, system instruction injection, and source attribution.
ConnectorNo auth
605,758 tools. Updated 2026-09-24 03:44
"RAG (Retrieval-Augmented Generation) system that can store papers and web pages" matching MCP tools:
- Ask a natural-language question and receive structured intelligence context retrieved from Tresslers Group dossiers via RAG (Retrieval Augmented Generation). Returns relevant document chunks, source citations, conviction metadata, and graph neighborhood data. The calling LLM should synthesize the returned context into a coherent answer.ConnectorNo auth
- Create a third-party LEAD-GENERATION page about a business (NOT a site for that business itself). Use this when the goal is to drive qualified search traffic to someone else's business — affiliate pages, review/guide pages, niche directories. The page is branded as an outside guide (e.g. "Best Roofers in San Diego"), refers to the business in the third person, and routes CTAs to the business's existing website. Differences from create_site: - Slug + page brand are SEO-vanity (e.g. "best-roofers-sandiego"), not the candidate's brand name. - Voice is third-party guide/reviewer — never first person. - Primary CTA is "visit their website"; phone/email demoted. - No specific pricing quoted; differentiators emphasized. - Locality is judged by category, not just address (IT/SaaS/agency stays category-wide even when a city is on file). Pass a business candidate object from search_businesses — that business is the one being PROMOTED. Requires authentication via API key (Bearer token). Generate an API key at webzum.com/dashboard/account-settings. The page generation happens in the background. Use get_site_status to check progress. Returns the businessId (a vanity slug) which can be used to access the page at /build/{businessId}.ConnectorDestructiveNo auth
- Semantic search over guthmann.estate — market insights, reports, neighborhood portraits, listing exposés, project pages and the company's own pages. Hybrid retrieval (vector + keyword, no reranking); one result per page with title, description, image, best-matching snippet and score. Use it for questions that need prose (analysis, context, advice); use the data tools for exact numbers and `listings` for what is currently for sale — the search index follows the website with up to six hours of delay. Parameters: - q: natural-language query, in the language of the pages you want (min 2 characters) - locale: "de" | "en" — language of the indexed pages (default: en) - section: comma-separated filter — "listings" (exposés), "projects" (new-build projects), "market-intelligence" (insights, reports, portraits), "pages" (company, services, guides); omit for all - limit: 1-20 pages (default: 10) Key response fields: - url, title, description, image, section, language - snippet (best-matching text passage), score (0-1)ConnectorNo auth
- Show ONE retrieved evidence document behind an answer you already received, addressed by that answer's correlation_id plus a document_id from its evidence_documents references. Returns the full stored document (title, body, metadata, embedding_text) with the retrieval rank and scores the answer recorded; never the raw embedding vector. Only documents the addressed answer actually recorded resolve: there is no fetch-by-id in general and no way to browse the store. Requires the persisted compliance log and the same session that produced the answer. Absent from the no-auth public demo.ConnectorNo auth
- READ PIPELINE step 3 — CITE, in batch. Get verbatim text + citation_link for SEVERAL pages of a single book in one round-trip, to assemble a multi-passage dossier. Specify either pages (an explicit array, e.g. [12, 40, 41]) or an inclusive from/to range. Max 25 pages per call. Each entry carries its own citation_link to present alongside the quote, and — on non-Latin-script pages that have one — a romanized layer to show between the original and the translation (AI apparatus, not a transcription). Every entry also carries `text_source`: `translation` normally, or `ocr_original` on a leaf that is already English, where the verbatim text is `original` and must be attributed as the source's own words rather than as a translation. One batch can mix both — a Latin volume can hold an English preface. Batch pages count toward the shared daily page budget (see get_book_text); this is a citation tool, and corpus-scale extraction belongs on the dataset API (sourcelibrary.org/dataset).ConnectorNo auth
Matching MCP Servers
- AlicenseBqualityDmaintenanceEnhances AI model capabilities with structured, retrieval-augmented thinking processes that enable dynamic thought chains, parallel exploration paths, and recursive refinement cycles for improved reasoning.124MIT
- AlicenseBqualityDmaintenanceEnables retrieval-augmented generation by embedding queries with a chosen provider (e.g., OpenAI) and searching supported vector stores (Pinecone, pgvector) to return relevant content.1Apache 2.0
Matching MCP Connectors
send-that-email MCP — wraps StupidAPIs (keyless — no credential needed)
tldr-pages community simplified man pages (cached 24h)
- Shows HTML content on a display: menus, dashboards, welcome pages, schedules or any custom design. slot 'live' (default) replaces the current content; slot 'idle' stores the default/fallback content shown when nothing live is active (idle requires admin scope). Always pass a short description so later content reads stay meaningful. Exactly one of html or base64_html. For external web pages use send_url; to edit current content call read_display_html first. For polished results load prompt render_premium_display_html or resource agentview://public/design-system. Requires content scope.ConnectorDestructiveNo auth
- Universal hybrid retrieval across the user's visible Uwear library: garments, avatars/models, locations, ArtDirections, uploaded files, and generation results. This is a finder, not a recommender. Use short keyword queries (2 to 5 words), one concept per call, or an exact name/SKU/ID. Every word must match for lexical results; long sentences can return no lexical matches. A query describing one garment finds that garment, not complementary garments. Vector results stay close to the best match. Use this before opening the picker, e.g. 'SKU 42', 'urban art direction', 'summer denim', or 'studio model'. For saved outfits, retrieve matching garments first, then call list_outfits with clothing_item_ids or propose_outfits from the garment IDs. Returns stable typed IDs, ids_by_type, detail_tool/detail_arguments, and selection hints; for saved ArtDirections, use the returned art_direction_id in briefs. This combines current lexical metadata with maintained vector retrieval. Interactive searches do not refresh the index. indexed_count is always 0 here; it is not index coverage.ConnectorNo auth
- Download a file from a public http(s) URL and store it in the user's Second Brain as a file object — use when the user shares a direct link to a PDF, image, spreadsheet, or other file and asks to save, download, or keep it. The saved file shows up with their uploads and can be read afterwards with read_file. Not for web pages (that is read_web_page with save=true) and not for files behind a sign-in. Files over 50MB are refused.ConnectorNo auth
- Search Scholar Feed's 600k+ CS/AI/ML paper corpus. Semantic (embedding) search by default, so it finds conceptually related work even when the wording differs. EVERY PARAMETER DOCUMENTS ITS OWN BEHAVIOUR AND COVERAGE LIMITS — read the ones you intend to use; this description covers only what no single parameter can tell you. RETRIEVAL LIMIT: semantic ranking favours recent, stylistically-matched papers and routinely MISSES the old high-citation anchor of a field (H2O for KV eviction, GRIT for unified embedding+generation). To reach a field's canonical work, read the top-5 abstracts for repeated baseline mentions ('we compare against X') and look that name up directly, or call get_foundational_lineage. THREE UNRELATED NOTIONS OF IMPACT, easily confused: proven citations (sort='impactful', min_citations) | a ~90-day forecast percentile that is NULL on older papers and therefore excludes them (sort='trending', impact_min) | GitHub adoption (sort='community', min_stars). YOUR LIBRARY IS MARKED INLINE on authenticated calls: each hit carries is_saved and is_read, and a hit you previously annotated carries note_text — your own earlier verdict. Read note_text INSTEAD of re-deriving a conclusion from the abstract; re-judging a paper you already ruled on is the most common way an agent wastes a research session. is_saved=false is a real measurement; on anonymous calls these keys are absent entirely, so never read a missing is_saved as false. Papers new to you are ranked exactly as before — nothing is demoted for being unseen.ConnectorNo auth
- Read a page and get a deterministic verdict on whether the retrieval can be trusted, with evidence. PRIVATE BETA. Verified browser-based web content retrieval for AI agents. Same retrieval as POST /v1/extract ($0.005), plus what an agent needs to trust the result without re-fetching it: declared block detection (HTTP status and blocking-page signatures), non-empty validation, content consistency checks against navigation-dominant and templated extractions, a retrieval timestamp, and evidence metadata including the final URL after redirects, character and word counts, and a sha256 checksum of the returned markdown. Every check is deterministic: no model runs in this path, so two calls on the same page return the same verification. Failed checks are DECLARED alongside the content, never hidden. This does not bypass CAPTCHA or authentication and makes no claim to defeat anti-bot systems: it detects blocking and says so. — $0.020012/call, paid per request via x402 (USDC). Use when asked: "read this page with proof", "was this page blocked", "verified page retrieval".ConnectorNo auth
- Read the full text of one Celestia whitepaper or research PDF by slug. Celestia papers only — not arbitrary web PDFs (use a web-search tool for those). Call list_whitepapers first to get a valid slug.ConnectorNo auth
- Store a sealed OAuth2 authorization code. Called by the serverless callback function after the browser redirect. The ``state`` carries BOTH the patron npub (the lookup/retrieve key) and the operator npub (the PUBLIC key the code is sealed to) — see the SDK's ``pack_oauth_state``. The code is sealed with NIP-44 to the operator so only that operator's nsec can open it; the Neon row is keyed by the patron npub, so retrieval (``retrieve_code(state=patron_npub)``) is unchanged.ConnectorNo auth
- Use ONLY for a general storefront audit, readiness score, or fix recommendations. Do NOT use it to inspect a specific update or release; use preflight_woo_store for that. Check whether a public WooCommerce storefront is readable by shopping agents. Provide the store's HTTPS origin. The tool reads only public pages and the public WooCommerce Store API, changes nothing, and returns aggregate checks and recommendations without product text or customer data. When the storefront cannot be read at all, the tool abstains: state is UNREADABLE, score and grade are null, and the caller must not present that as a finding about the store.ConnectorNo auth
- List the authenticated user's existing characters (AI influencers) so you can pick a characterId for the other generation tools. There is no tool to CREATE a character -- that happens in the RYLA app at app.ryla.ai.ConnectorNo auth
- Returns CANDIDATE FOUNDATIONAL PAPERS for a research topic — cheap retrieval only, no synthesis. Ranks papers by a blend of citation count (0.6 weight, captures importance) and semantic similarity to your topic (0.4 weight). Use this to bootstrap a literature survey or get a fast sense of the landscape. For a synthesized orientation report (key concepts, open problems, reading order), use the /field-guide skill which calls this tool internally. Does not require a Pro API key — no LLM calls are made.ConnectorNo auth
- Store a client so invoice_create can refer to them by name. Re-adding the same name updates the stored address, email and VAT id; a record identical to a stored one is refused, naming the id that already holds it.ConnectorNo auth
- Fetch clean, parsed content for URLs you already have — from a search result, a sitemap, or a user. `urls` is required and takes several at once. Returns `results[]` with `url`, `title`, `raw_content` and `images`, plus a `failed_results[]` array — **read that one**, because a page that could not be fetched is reported there rather than raising an error. Choose `format` (markdown or text) and `extract_depth`. Measured at about 1 second for one page. Use this instead of `post_tavily_search` whenever you can already name the pages; searching for pages you can name costs more and may not return them. For a long list that can wait, `post_firecrawl_batch_scrape` runs it as a background job. To discover the URLs of a whole site first, use `post_tavily_map`.ConnectorOAuth
- Find coupon / promo / discount codes for an online store. Pass the store domain or any URL from the store (product, cart or checkout page). Returns codes ordered by how likely they are to work: try them at checkout from the top, keep the one that lowers the total the most. Codes can expire or carry store restrictions, so none is guaranteed; an empty list means none are known for that store.ConnectorNo auth
- Retrieve and verify evidence from one public web URL using direct HTTP retrieval. Use when: the request is specifically about the content and provenance of a URL. Do not use when: evidence must be synthesized for a company (use siteborne_build_company_evidence_graph), extracted from an authorized document (use siteborne_extract_document_evidence_json), checked against an existing output contract (use siteborne_verify_agent_output), or the page requires JavaScript rendering (rendered retrieval is not available). Parameters: retrieval_mode must be direct; rendered is defined but unavailable and is rejected before any payment challenge, never substituted with direct retrieval. output_mode structured needs buyer_schema and field_selectors to be meaningful; redirect_policy and max_redirects bound redirect following; max_content_size bounds returned bytes; maximum_authorized_price only constrains payment and never changes retrieval scope. Behavior: open-world: a paid request performs bounded outbound HTTP retrieval of the target URL through a safe-egress boundary (private and loopback destinations are refused) and persists governed payment, audit, job and Workflow state; an unpaid request returns payment_required; a repeated identical request with the same payment is replay-protected and is not charged twice. Retrieval admission follows the governed runtime rate policy; no fixed public per-origin rate is promised. This service is currently production-enabled. Economics: exact price of $0.008 USD per request in direct mode; the payment challenge requires that amount and the charge settles at exactly that amount. rendered mode has a governed price of $0.029 USD but is not available: it is rejected before any payment challenge and never substituted. Failure: schema-invalid input and unavailable modes are rejected before any payment challenge; target-site errors, timeouts and unavailable retrieval return a structured MCP error and are never answered with a substitute result. Returns: normalized, source-attributed web context with verification and PCC evidence.ConnectorNo auth
- Store a client so invoice_create can refer to them by name. Re-adding the same name updates the stored address, email and VAT id; a record identical to a stored one is refused, naming the id that already holds it.ConnectorNo auth