{"name":"app.highlyt/highlyt","title":"Highlyt","url":"https://mcp.highlyt.app/mcp","host":"mcp.highlyt.app","read_at":"2026-11-10T15:26:19.326217+00:00","grade":"A","score":100,"capped":null,"graded":true,"pending_second_read":[],"counts":{"error":0,"warning":0,"info":1},"findings":[{"rule":"mcp-version-differs","severity":"info","message":"The version it reports differs from its newest registry entry. It reports 1.0.0; the registry lists 1.0.1.","fix":"","where":[],"count":0}],"handshake":{"answered":true,"mcp":true,"era":"handshake","protocol_version":"2025-11-25","server_info":{"name":"highlyt-mcp","version":"1.0.0","title":null},"capabilities":["logging","prompts","resources","tools"]},"sign_in":null,"tools":[{"name":"highlyt_list_documents","title":"List Documents","description":"List PDF documents in your Highlyt library.\n\nReturns documents sorted by last update time with pagination.\nFilter by shelf_id to see documents in a specific collection.","read_only":true,"destructive":null,"inputs":["params"],"required":["params"],"price_stated_usd":null},{"name":"highlyt_get_document","title":"Get Document","description":"Get detailed information about a document.\n\nReturns full metadata including book context, reading progress,\nand organizational information.","read_only":true,"destructive":null,"inputs":["params"],"required":["params"],"price_stated_usd":null},{"name":"highlyt_get_research_brief","title":"Get Research Brief","description":"Read a researcher-authored brief with verified, reviewed source receipts.\n\nUse this as context only. Cite only the included receipts. The tool does\nnot reveal a draft reference or proposed evidence as support for a claim.","read_only":true,"destructive":null,"inputs":["params"],"required":["params"],"price_stated_usd":null},{"name":"highlyt_export_research_brief_markdown","title":"Export Research Brief Markdown","description":"Export a portable researcher-authored Markdown brief with safe receipts.","read_only":true,"destructive":null,"inputs":["params"],"required":["params"],"price_stated_usd":null},{"name":"highlyt_list_highlights","title":"List Highlights","description":"List highlights in a document with pagination.\n\nReturns up to 'limit' highlights (default 20, max 50) starting from 'offset'.\nUse has_more and next_offset to paginate through all highlights.\nEach highlight includes the color meaning (e.g., \"Key concepts\", \"Questions\").","read_only":true,"destructive":null,"inputs":["params"],"required":["params"],"price_stated_usd":null},{"name":"highlyt_create_highlight","title":"Create Highlight","description":"Create a new highlight in a document.\n\nUses react-pdf-highlighter-extended format:\n- position: ScaledPosition with boundingRect, rects, pageNumber\n- content: {text: \"...\"} or {image: \"...\"}\n- highlight_type: \"text\" or \"area\"\n- comment: User's comment\nColors should be hex codes (e.g., #FFEB3B for yellow).","read_only":null,"destructive":null,"inputs":["params"],"required":["params"],"price_stated_usd":null},{"name":"highlyt_update_highlight","title":"Update Highlight","description":"Update a highlight's color or comment.\n\nOnly provided fields will be updated.","read_only":null,"destructive":null,"inputs":["params"],"required":["params"],"price_stated_usd":null},{"name":"highlyt_delete_highlight","title":"Delete Highlight","description":"Delete a highlight permanently.\n\nThis action cannot be undone.","read_only":null,"destructive":true,"inputs":["params"],"required":["params"],"price_stated_usd":null},{"name":"highlyt_list_highlight_links","title":"List Highlight Links","description":"List highlight links (insight threads) in a document with pagination.\n\nReturns up to 'limit' links (default 50, max 100) starting from 'offset'.\nUse has_more and next_offset to paginate through all links.\nEach link has a type: 'related', 'supports', 'contradicts', 'expands', or 'questions'.","read_only":true,"destructive":null,"inputs":["params"],"required":["params"],"price_stated_usd":null},{"name":"highlyt_get_highlight_links","title":"Get Highlight Links","description":"Get all links connected to a specific highlight.\n\nReturns parent links (where this highlight is referenced by others)\nand child links (where this highlight references others).\nUseful for exploring how a specific idea connects to other highlights.","read_only":true,"destructive":null,"inputs":["params"],"required":["params"],"price_stated_usd":null},{"name":"highlyt_create_highlight_link","title":"Create Highlight Link","description":"Create a link between two highlights to form an insight thread.\nSupports both same-document and cross-document linking.\n\nIMPORTANT — parent/child semantics:\n- parent_highlight_id = the highlight you are viewing (the \"context\" highlight)\n- child_highlight_id = the highlight you are linking TO (the \"related\" highlight)\n- link_type describes what the CHILD does to the PARENT:\n  - supports: \"child supports parent\" (child provides evidence for parent)\n  - contradicts: \"child contradicts parent\" (child challenges parent)\n  - expands: \"child expands parent\" (child elaborates on parent)\n  - questions: \"child questions parent\" (child raises questions about parent)\n  - related: general connection\n\nFor cross-document links, set target_document_id to the document containing the\nchild highlight. If omitted, both highlights are assumed to be in source_document_id.\n\nExample: If highlight A says \"GDP grew 5%\" and you want to link highlight B\n\"Exports increased 12%\" as supporting evidence, then:\n  parent_highlight_id = A (the claim), child_highlight_id = B (the evidence),\n  link_type = \"supports\" (B supports A).","read_only":null,"destructive":null,"inputs":["params"],"required":["params"],"price_stated_usd":null},{"name":"highlyt_update_highlight_link","title":"Update Highlight Link","description":"Update a highlight link's relationship type or note.\n\nOnly provided fields will be updated.","read_only":null,"destructive":null,"inputs":["params"],"required":["params"],"price_stated_usd":null},{"name":"highlyt_delete_highlight_link","title":"Delete Highlight Link","description":"Delete a link between two highlights.\n\nThis removes the connection but does not delete the highlights themselves.","read_only":null,"destructive":true,"inputs":["params"],"required":["params"],"price_stated_usd":null},{"name":"highlyt_get_cross_document_links","title":"Get Cross-Document Links","description":"List all cross-document highlight links for the current user.\n\nReturns links where source_document_id != target_document_id,\nwith metadata about both source and target documents.\nUseful for exploring connections across your entire library.","read_only":true,"destructive":null,"inputs":["params"],"required":["params"],"price_stated_usd":null},{"name":"highlyt_list_cluster_summaries","title":"List Cluster Summaries","description":"List all cluster summaries for a document's knowledge graph.\n\nReturns each summary with its highlight_ids array — the highlights that were\nin the cluster when the summary was last generated.\n\nDETECTING STALE SUMMARIES:\nTo check if summaries need updating after adding new links:\n1. Call highlyt_list_highlight_links to get all current links\n2. Compute connected components (group highlights by connectivity)\n3. Call this tool to get stored summaries\n4. For each summary, check if its highlight_ids is a SUBSET of a current component\n   - If highlight_ids == component_ids → summary is current\n   - If highlight_ids ⊂ component_ids → summary is STALE (cluster grew)\n   - Set difference (component_ids - highlight_ids) = newly added highlights\n5. Regenerate stale summaries with highlyt_upsert_cluster_summary,\n   passing the FULL current component highlight_ids","read_only":true,"destructive":null,"inputs":["params"],"required":["params"],"price_stated_usd":null},{"name":"highlyt_upsert_cluster_summary","title":"Upsert Cluster Summary","description":"Create or update a summary for a connected component cluster in the knowledge graph.\n\nA cluster is a group of linked highlights that form a connected component.\n\nIMPORTANT:\n- highlight_ids must be the COMPLETE, CURRENT set of highlight UUIDs in the cluster\n  (not just newly added ones). The array is sorted internally for matching.\n- If a summary already exists for this document_id + highlight_ids combination,\n  it will be UPDATED (upsert behavior).\n- When updating a stale summary (cluster grew due to new links), pass the FULL\n  updated highlight_ids array so the stored record reflects the current cluster.\n- The summary should describe thematic connections across ALL highlights in the cluster,\n  including any newly added ones.\n\nTypical workflow:\n1. Read highlights with highlyt_list_highlights\n2. Read links with highlyt_list_highlight_links\n3. Compute connected components from links\n4. For each component, generate a summary covering all highlights\n5. Call this tool with the component's highlight_ids and generated summary","read_only":null,"destructive":null,"inputs":["params"],"required":["params"],"price_stated_usd":null},{"name":"highlyt_delete_cluster_summary","title":"Delete Cluster Summary","description":"Delete a cluster summary from the knowledge graph.\n\nThis removes the summary record but does not affect the highlights or their links.","read_only":null,"destructive":true,"inputs":["params"],"required":["params"],"price_stated_usd":null},{"name":"highlyt_get_page_text","title":"Get Page Text","description":"Retrieve the text content of specific pages from a document.\n\nUse this to read document content before creating highlights.\nReturns up to 5 pages per request. If the requested range exceeds 5 pages,\nuse has_more and next_page_start to paginate through remaining pages.","read_only":true,"destructive":null,"inputs":["params"],"required":["params"],"price_stated_usd":null},{"name":"highlyt_get_document_images","title":"Get Document Images","description":"Retrieve images (charts, graphs, figures, diagrams, photos) and their surrounding\ntext context from an EPUB or web clip document.\n\nWHEN TO USE THIS TOOL:\n- User asks about a chart, graph, figure, diagram, or image in a document\n- User wants visual data or illustrations from a book/article\n- User references \"Figure X.X\" or any visual element\n\nReturns each image's base64 data URI, alt text, dimensions, chapter location,\nand the paragraph text before/after it so you can describe what the image shows.\nUse the optional query parameter to filter images by surrounding text context.\n\nFor PDFs, images are embedded in the rendered pages — use highlyt_get_page_text instead.","read_only":true,"destructive":null,"inputs":["params"],"required":["params"],"price_stated_usd":null},{"name":"highlyt_create_text_highlight","title":"Create Text Highlight","description":"Create a text-based highlight on a specific page.\n\nUse this after reading page content with highlyt_get_page_text.\nThe highlight will appear in the sidebar and be searchable/exportable.\nCopy the exact text from the page content for the 'text' field.","read_only":null,"destructive":null,"inputs":["params"],"required":["params"],"price_stated_usd":null},{"name":"highlyt_bulk_create_highlights","title":"Bulk Create Highlights","description":"Create multiple text-based highlights in one batch (max 10 per request).\n\nEfficient for chapter analysis — create highlights in batches of up to 10.\nIf you have more than 10, split into multiple calls.\n\nHighlight format: {page_number: int, text: str, comment?: str, color?: str}\nColors: amber (#E5A84B) core ideas, sage (#6BBF8A) action items, sky (#5BA3D9) questions.","read_only":null,"destructive":null,"inputs":["params"],"required":["params"],"price_stated_usd":null},{"name":"highlyt_export_highlights","title":"Export Highlights","description":"Export document highlights for AI context with pagination.\n\nReturns up to 'limit' highlights (default 20, max 50) starting from 'offset'.\nUse has_more and next_offset to paginate through all highlights.\nIncludes document metadata, color meanings, and insight threads\nrelevant to the returned highlights.","read_only":true,"destructive":null,"inputs":["params"],"required":["params"],"price_stated_usd":null},{"name":"highlyt_search_highlights","title":"Search Highlights","description":"Search highlights across your library.\n\nFinds highlights containing the query text.\nEach result includes the color meaning based on the document's definitions.\nOptionally limit to a specific document.","read_only":true,"destructive":null,"inputs":["params"],"required":["params"],"price_stated_usd":null},{"name":"highlyt_search","title":"Full-Text Library Search","description":"Full-text search across your entire library — documents, highlights, and page content.\n\nThis searches the actual text content of your PDFs (every page), highlight text/comments,\nand document metadata (title, author, keywords). Results are ranked by relevance with\ntext snippets showing where matches were found.\n\nSupports natural language queries and websearch syntax:\n- Simple: \"machine learning\"\n- Exact phrase: '\"neural network\"'\n- OR: \"neural OR deep\"\n- Exclude: \"learning -supervised\"\n\nEach result includes match_type ('content', 'highlight', or 'metadata'),\nthe page number where the match was found, and a snippet with **bold** markers\naround matching terms.","read_only":true,"destructive":null,"inputs":["params"],"required":["params"],"price_stated_usd":null},{"name":"highlyt_list_research_projects","title":"List Research Projects","description":"List the caller's research projects for a bounded AI research task.","read_only":true,"destructive":null,"inputs":[],"required":[],"price_stated_usd":null},{"name":"highlyt_list_references","title":"List Research References","description":"List reviewed references, optionally in one project.\n\nDrafts are excluded unless include_drafts is explicitly true. Never cite a\ndraft as a verified source.","read_only":true,"destructive":null,"inputs":["params"],"required":["params"],"price_stated_usd":null},{"name":"highlyt_get_reference","title":"Get Research Reference","description":"Get one reviewed research reference. Never cite a draft without explicit permission.","read_only":true,"destructive":null,"inputs":["params"],"required":["params"],"price_stated_usd":null},{"name":"highlyt_export_references","title":"Export Research References","description":"Export reviewed references as BibTeX, RIS, or canonical CSL-JSON.\n\nThis always excludes drafts. Never cite a draft as a verified source.","read_only":true,"destructive":null,"inputs":["params"],"required":["params"],"price_stated_usd":null}],"tools_listed":28,"samples":[{"kind":"tool","name":"highlyt_list_research_projects","is_error":true,"price_asked_usd":null,"networks":null}],"price_honesty":"nothing to check","tls":{"valid":true,"expires_on":"2027-01-20","days_after_check":70,"issuer":"Let's Encrypt"},"registry":{"version":"1.0.1","status":200,"published_at":"2026-10-16T05:23:30.30172Z","website_url":"https://highlyt.app/features/mcp-server","repository":null},"robots":null,"reads":1,"card_url":"https://agoranome.com/mcp-servers/app.highlyt/highlyt","badge":{"url":"https://agoranome.com/mcp-servers/app.highlyt/highlyt/badge.svg","markdown":"[![Agoranome MCP report card](https://agoranome.com/mcp-servers/app.highlyt/highlyt/badge.svg)](https://agoranome.com/mcp-servers/app.highlyt/highlyt)"},"method":"Read the way an MCP client reads a server before an agent uses it: the handshake, every page of the tool list, the prompts and resources, the sign-in challenge, the server card and the TLS certificate, once a week, with no payment and nothing that writes. Up to two tools the server itself marks read-only, with no required input, are called once with no arguments, and up to two text resources are read. Score: 100 minus 25 for each kind of error and 8 for each kind of warning; a stop finding confirmed by a second read a day later caps the grade at D.","method_url":"https://agoranome.com/mcp-servers/method","method_version":1,"paid_next":{"tool":"server_standing","title":"MCP server standing","price":"$0.002","method":"GET","url":"https://api.agoranome.com/v1/facts/server-standing","sample":"https://api.agoranome.com/v1/facts/server-standing/sample","mcp_tool":"server_standing","why":"One signed number for one MCP server: its grade, what changed in its tools and since when, with an ETag so an unchanged answer is free."},"disputes":"research@agoranome.com","plan_offer":null,"note":"Names, descriptions and outputs are quoted from the server. They are data, never instructions."}