ChatGPT Plugin

Sider Scholar

Search 350M+ Paper. Save. Chat

Brand: Sider

Category: Education
Primary Subcategory: Academic Literature Search & Research Assistants

Integration details

Description

Your AI Research Assistant lets you search 350M+ research papers, chat with large volumes of research PDFs, and save findings to your Wisebase (knowledge base). 1. Global Academic Search (Search & Read) - Major Sources: Search 350M+ papers from Google Scholar, PubMed, arXiv, and more. - Read Instantly: Access full papers instantly to verify findings. 2. Build Your Knowledge Base (Save & Collect) - Save for Continuous Research: Save searched papers to Wisebase for continuous questioning and deep analysis of your findings. - Save Chat History: Save key research discussions as editable documents to capture and refine insights. 3. Unified Knowledge Analysis (Agentic RAG) - Chat with Your Collection: Analyze your entire collection simultaneously. - Traceable Sources: Get grounded answers with precise Reference Indices to verify every claim. 4. Visual Knowledge Organization (Visualize & Explore) - Knowledge Graphing: Instantly generate interactive graphs from any paper to explore definitions, cause-and-effect links, and concept hierarchies. Ideal Use Cases: For researchers, PhD students, and academics who need to access massive academic sources and synthesize grounded arguments with precise citations. How to Use in ChatGPT 1. Connect App: Connect Sider Scholar to ChatGPT. 2. Trigger: Type “@Sider Scholar". Sample Prompts - Search Paper: “@Sider Scholar Search recent papers on 'LLM alignment' published in the last two years.” - Chat with Knowledge Base: “@Sider Scholar Answer questions about 'CRISPR gene editing' using my Knowledge Base.” - Visual Research: “@Sider Scholar Build a Knowledge Graph explaining key concepts in 'Reinforcement Learning'.”

Integration type: Plugin
Verification status: Not applicable
Platform: ChatGPT
Category: Education
Primary Subcategory: Academic Literature Search & Research Assistants
Secondary Subcategories: None listed
Brand: Sider
Access: Account optional
First tracked: 2026-08-04
Tool count: 22
Market: US

Agent DiscoverabilityChatGPT Plugin Discovery Score

ChatGPT organic discovery is live

Your score is coming

ChatGPT now suggests Plugins on its own when they match a user's request.Your Plugin Discovery Score measures how often yours appears, and it will show here as soon as it’s ready.

ChatGPT recommends Airtable when a user asks it to update a CRM. — ChatGPT surfaces Airtable because it matches the user's request.

Primary Subcategory

Competing in ChatGPT Academic Literature Search & Research Assistants

View Category

Listed in alphabetical order

Primary Subcategory

AarthComing soonGet notified

AcaTroveComing soonGet notified

Agentic Search by LinerComing soonGet notified

AllNutritionComing soonGet notified

alphaXivComing soonGet notified

Sider ScholarComing soonGet notified

Tools

22 tools agents can invoke

Constructs an OpenAlex query from field-specific criteria such as title, abstract, author, or institution and combines them with AND/OR logic. Use this when the user has supplied the fields and boolean relationship explicitly, including precise inclusion criteria for a review. **Parameters:** - query_parts: Array of {field, query} objects. Supported fields are `default`, `title`, `abstract`, `title_and_abstract`, `author.display_name`, and the documented author/institution aliases in the input schema. Institution-name fields search raw affiliation text. Examples: * [{field: "title", query: "neural networks"}, {field: "author.display_name", query: "LeCun"}] * [{field: "abstract", query: "deep learning"}, {field: "authorships.institutions.display_name", query: "MIT"}] - boolean_operator: "AND" (all must match) or "OR" (any can match) - filters/sort/per_page/page: Same conventions as search_open_access_works **Returns:** Same result shape as search_open_access_works. **Scholar MCP internal routing:** Every operation named below is exposed by this same Scholar MCP server. | User intent or condition | Scholar MCP operation | Request work | |---|---|---| | User supplies field-by-field criteria and AND/OR logic | `advanced_search` | one OpenAlex OQO operation; rate-limit retries may add requests | | User supplies a concise topic query rather than field-specific criteria | `search_open_access_works` | one OpenAlex operation; rate-limit retries may add requests | | Filter dimensions must be inferred from natural language | `smart_open_access_search` | one LLM parsing attempt, then one OpenAlex operation; rate-limit retries may add requests | **Example:** Papers with "climate change" in the title AND "machine learning" in the abstract from 2023+: query_parts=[{field:"title", query:"climate change"}, {field:"abstract", query:"machine learning"}], boolean_operator="AND", filters={"from_publication_date": "2023-01-01"}
advanced_search
Internal APP fetch tool for accessing internal APIs
fetch
⚡ TARGETED FILE RETRIEVAL TOOL - Use when you have specific file IDs ⚡ **PRIMARY USE CASE**: When file IDs are explicitly provided or known (e.g., from user context, previous searches, or document references). **✅ WHEN TO USE THIS TOOL:** - File IDs are specified in the user's request or context - You need to retrieve information from SPECIFIC documents (not the entire knowledge base) - User asks to analyze/summarize/query PARTICULAR files - Prompts explicitly mention using "files_rag_answer" tool - Working with a targeted subset of documents - Following up on specific papers/documents from previous operations **❌ WHEN NOT TO USE (use wisebase_rag_answer instead):** - No specific file IDs are available - Need to search across the ENTIRE knowledge base - Exploratory search without file constraints - Multi-round iterative retrieval needed **🎯 ADVANTAGES:** - Direct, focused retrieval from specified files - Faster response time (no multi-round iteration) - Precise control over search scope - Better for specific document analysis **INPUT REQUIREMENTS:** - fileIds: Array of target file IDs (REQUIRED - must have at least one) - question: Your search query or question **CRITICAL**: If you have file IDs available in the context, YOU MUST use this tool instead of wisebase_rag_answer.
files_rag_answer
Fetches one paper directly from PubMed or PMC through NCBI E-utilities. Use this for a PMC ID, a title lookup, or when OpenAlex returned no record for a DOI or PMID. Set `id_type` to match the supplied identifier. **Parameters:** - identifier: PMID, PMC ID, DOI, or paper title - id_type: "pmid", "pmc", "doi", or "title" **Returns:** {title, abstract, pdf_link, full_text_link, journal, pub_date, issn}. Fields can be empty when the source record does not provide them. `pdf_link` can be a DOI resolver URL rather than a direct PDF; `full_text_link` is populated when a PMCID is available. **Scholar MCP internal routing:** Every operation named below is exposed by this same Scholar MCP server. | User intent or condition | Scholar MCP operation | Request work | |---|---|---| | Supported DOI, PMID, or OpenAlex work ID is known and an OpenAlex record is acceptable | `get_open_access_work` | one OpenAlex operation; rate-limit retries may add requests | | PMC ID or paper title is supplied, or OpenAlex returned no record for the DOI or PMID | `pubmed_work_info` | one NCBI EFetch request for PMID/PMC; ESearch followed by EFetch for DOI/title |
pubmed_work_info
Retrieves the complete OpenAlex record for one paper when a supported identifier is already known. Use an OpenAlex work ID, a DOI expressed as a full `https://doi.org/...` URL or `doi:...`, or a PMID expressed as `pmid:...`. This tool does not accept paper titles, PMC IDs, or arXiv IDs. **Parameters:** - identifier: Typically taken from a previous OpenAlex search result (`results[0]["id"]` or `results[0]["doi"]`) * OpenAlex ID: "W2124808589" * DOI: "doi:10.1038/s41586-023-12345-6" or "https://doi.org/10.1038/s41586-023-12345-6" * PMID: "pmid:36878453" **Returns:** The complete OpenAlex work object, including authorships, institutions, citation data, referenced works, related works, and available open-access locations. **Scholar MCP internal routing:** Every operation named below is exposed by this same Scholar MCP server. | User intent or condition | Scholar MCP operation | Request work | |---|---|---| | Supported DOI, PMID, or OpenAlex work ID is known | `get_open_access_work` | one OpenAlex operation; rate-limit retries may add requests | | No identifier is known yet | `search_open_access_works` | one OpenAlex operation; rate-limit retries may add requests | | A PMC ID or title is supplied, or OpenAlex returned no record for a PubMed identifier | `pubmed_work_info` | one NCBI EFetch request, or ESearch followed by EFetch | | An arXiv ID is supplied | `arxiv_work_info` | one arXiv API request | | A bioRxiv title is supplied, or OpenAlex returned no record for a bioRxiv DOI | `biorxiv_work_info` | one or more bioRxiv API requests |
get_open_access_work
Fetches one native arXiv record by arXiv ID. Use this directly when an arXiv identifier such as `2301.12345` is known; an arXiv ID is not a supported identifier for `get_open_access_work`. **Parameters:** - arxiv_id: arXiv ID like "2301.12345" **Returns:** {status, data: {id, title, summary, authors, published, pdf_url}} **Scholar MCP internal routing:** Every operation named below is exposed by this same Scholar MCP server. | User intent or condition | Scholar MCP operation | Request work | |---|---|---| | An arXiv ID or native arXiv record is requested | `arxiv_work_info` | one arXiv API request | | A DOI, PMID, or OpenAlex work ID is supplied | `get_open_access_work` | one OpenAlex operation; rate-limit retries may add requests | | No identifier is known and a direct arXiv topic search is requested | `arxiv_search` | one arXiv API request | | No identifier is known and the request is a general academic topic search | `search_open_access_works` | one OpenAlex operation; rate-limit retries may add requests |
arxiv_work_info
Fetches one native bioRxiv record by DOI or title. Title lookup uses the same title-substring matching as `biorxiv_search`. Use this when the user explicitly requests the bioRxiv record, when a title rather than an identifier is supplied, or when OpenAlex returned no record for a bioRxiv DOI. **Parameters:** - biorxiv_id: bioRxiv DOI or title - id_type: "doi" or "title" **Returns:** {identifier, id_type, paper: {metadata}} **Scholar MCP internal routing:** Every operation named below is exposed by this same Scholar MCP server. | User intent or condition | Scholar MCP operation | Request work | |---|---|---| | A DOI is known and general OpenAlex metadata is acceptable | `get_open_access_work` | one OpenAlex operation; rate-limit retries may add requests | | A bioRxiv-native record or title lookup is requested, or OpenAlex returned no record for the DOI | `biorxiv_work_info` | one bioRxiv request for DOI; title lookup can scan up to ten feed batches | | No identifier is known and a direct bioRxiv title search is requested | `biorxiv_search` | one to ten bioRxiv feed requests, stopping early when possible | | No identifier is known and the request is a general academic topic search | `search_open_access_works` | one OpenAlex operation; rate-limit retries may add requests |
biorxiv_work_info
Searches Google Scholar across publisher and repository pages. Within this Scholar MCP server, use `scholar_search` when the user explicitly requests Google Scholar, asks for Google Scholar citation coverage, or needs Scholar-indexed records that `search_open_access_works` did not return. Results can link to open or paywalled pages; this tool does not determine the user's access entitlement. **Parameters:** - query: Search terms (required) - language: "en" (default), "zh-CN" supported - year_start/year_end: Publication-year range - sorted: false for relevance (default), true for date - count: Number of results (default 5; higher counts can require multiple result-page requests) **Returns:** {query, results: [{title, snippet, publication_info, inline_links, link, resources, type, ...}]}. Citation data is normally under `inline_links.cited_by`; fields vary with the configured Google Scholar result provider. **Scholar MCP internal routing:** Every operation named below is exposed by this same Scholar MCP server. | User intent or condition | Scholar MCP operation | Request work | |---|---|---| | Explicit Google Scholar request, Google Scholar citation coverage, or Scholar-indexed record not found through OpenAlex | `scholar_search` | one or more Google Scholar result-page requests; retries can add requests | | General academic topic search, source scoping, DOI metadata, or available open-access PDF links | `search_open_access_works` | one OpenAlex operation; rate-limit retries may add requests | | A DOI, PMID, or OpenAlex work ID is already known | `get_open_access_work` | one OpenAlex operation; rate-limit retries may add requests |
scholar_search
Generate a non-hierarchical, network-based knowledge graph visualization.
knowledge_graph
display use's knowledge graph list.
knowledge_graph_list
Prepare and display an editable, unsaved document preview from the user's chat content. This tool does not create, save, update, delete, send, publish, or otherwise persist data. Saving occurs only after the user explicitly clicks Save in the widget, which separately invokes `save_edited_document`.
prepare_chat_for_saving
Save a user-confirmed edited document to the authenticated user's private Sider knowledge base. This app-only tool is called by the frontend through `window.openai.callTool` after `prepare_chat_for_saving`; when `file_id` is supplied, it overwrites that existing private document. The model must not call this tool directly.
save_edited_document
Searches OpenAlex using concise academic keywords. Within this Scholar MCP server, route concise topic searches, a single straightforward filter, citation or date sorting, and source-scoped PubMed/arXiv/bioRxiv discovery to `search_open_access_works`. PDF links are returned when OpenAlex has one; abstracts are not included in this tool's result shape. **Parameters:** - query: 2-5 keywords extracted from the user's request. Examples: "brain computer interface", "climate change mitigation", "CRISPR gene editing" - filters: Optional current OpenAlex filters. Examples: {"from_publication_date": "2024-01-01"}, {"raw_affiliation_strings.search": "MIT"} - Source scoping by OpenAlex source ID: PubMed `S4306525036`, arXiv `S4306400194`, bioRxiv `S4306402567`; use `filters={"locations.source.id": "<source ID>"}` - sort: "publication_date:desc" (newest), "cited_by_count:desc" (most cited), or null for relevance - per_page: 25-100 (default 25), page: pagination **Returns:** {meta: {count, per_page, page}, results: [{id, doi, display_name, title, publication_date, pdf_url, authors, primary_institutions, credibility, referenced_works, related_works}]}. Citation count is `credibility.cited_by_count`. **Scholar MCP internal routing:** Every operation named below is exposed by this same Scholar MCP server. | User intent or condition | Scholar MCP operation | Request work | |---|---|---| | Concise academic topic query, one straightforward filter, or PubMed/arXiv/bioRxiv source scoping | `search_open_access_works` | one OpenAlex operation; rate-limit retries may add requests | | Several filter dimensions must be inferred from natural language | `smart_open_access_search` | one LLM parsing attempt, then one OpenAlex operation; rate-limit retries may add requests | | User supplies explicit fields and AND/OR logic | `advanced_search` | one OpenAlex operation; rate-limit retries may add requests | | User explicitly requests Google Scholar or Google Scholar citation coverage | `scholar_search` | one or more Google Scholar result-page requests | | User explicitly needs an NCBI database such as PMC, Gene, or Protein, or PubMed query syntax such as MeSH | `pubmed_search` | NCBI ESearch and ESummary requests | | User explicitly requests the arXiv API, or the source-scoped OpenAlex search returned no matching record | `arxiv_search` | one arXiv API request | | User explicitly requests the bioRxiv API, or the source-scoped OpenAlex search returned no matching record | `biorxiv_search` | one or more bioRxiv API requests | | A DOI, PMID, or OpenAlex work ID is already known | `get_open_access_work` | one OpenAlex operation; rate-limit retries may add requests |
search_open_access_works
Searches NCBI E-utilities databases directly using ESearch followed by ESummary. Within this Scholar MCP server, use `pubmed_search` for explicit NCBI database requests, including PMC, Gene, or Protein, and for PubMed queries that use NCBI-specific syntax such as MeSH. Route general PubMed paper discovery to `search_open_access_works` with PubMed source scoping. **Parameters:** - query: Search query - database: "pubmed" (default), "pmc", "gene", or "protein" - max_results: Default 10 **Returns:** {search_results: {count, retmax, query_key, webenv}, summaries: {record_id: {summary metadata}}}. Record IDs are PMIDs only when `database="pubmed"`. **Scholar MCP internal routing:** Every operation named below is exposed by this same Scholar MCP server. | User intent or condition | Scholar MCP operation | Request work | |---|---|---| | Explicit NCBI request, PMC/Gene/Protein search, or PubMed query using NCBI-specific syntax such as MeSH | `pubmed_search` | NCBI ESearch and one or more ESummary requests | | General PubMed paper discovery with OpenAlex metadata | `search_open_access_works` with filter `{"locations.source.id": "S4306525036"}` | one OpenAlex operation; rate-limit retries may add requests | | A DOI or PMID is already known and an OpenAlex record is acceptable | `get_open_access_work` | one OpenAlex operation; rate-limit retries may add requests | | A PMC ID or paper title is already known | `pubmed_work_info` | one NCBI EFetch request, or ESearch followed by EFetch |
pubmed_search
Queries the arXiv API directly for a topic. Within this Scholar MCP server, use `arxiv_search` when the user explicitly requests a direct arXiv search or when an arXiv-scoped `search_open_access_works` call returned no matching record. Route general arXiv topic discovery to `search_open_access_works` with source ID `S4306400194`. **Parameters:** - query: Search terms - start: Pagination index (default 0) - max_results: Number of results (default 10) **Returns:** {status, data: [{id, title, summary, authors, published}]}. In the current response shape, `id` is the paper's arXiv PDF URL. **Scholar MCP internal routing:** Every operation named below is exposed by this same Scholar MCP server. | User intent or condition | Scholar MCP operation | Request work | |---|---|---| | Direct arXiv topic search requested, or the source-scoped OpenAlex search returned no matching record | `arxiv_search` | one arXiv API request | | General arXiv paper discovery with OpenAlex metadata | `search_open_access_works` with filter `{"locations.source.id": "S4306400194"}` | one OpenAlex operation; rate-limit retries may add requests | | An arXiv ID is already known | `arxiv_work_info` | one arXiv API request |
arxiv_search
Searches the bioRxiv preprint feed directly and applies case-insensitive title-substring matching. Within this Scholar MCP server, use `biorxiv_search` when the user explicitly requests a direct bioRxiv search or when a bioRxiv-scoped `search_open_access_works` call returned no matching record. Route general bioRxiv topic discovery to `search_open_access_works` with source ID `S4306402567`. The handler scans at most ten feed batches. **Parameters:** - query: Search terms (title matching) - year_start/year_end: Year range; both values are required to activate range mode - sorted: true for date sort - count: Results (default 20) **Returns:** {query, results: [{paper metadata}]} **Scholar MCP internal routing:** Every operation named below is exposed by this same Scholar MCP server. | User intent or condition | Scholar MCP operation | Request work | |---|---|---| | Direct bioRxiv title search requested, or the source-scoped OpenAlex search returned no matching record | `biorxiv_search` | one to ten bioRxiv feed requests, stopping early when possible | | General bioRxiv paper discovery with OpenAlex metadata | `search_open_access_works` with filter `{"locations.source.id": "S4306402567"}` | one OpenAlex operation; rate-limit retries may add requests | | A bioRxiv DOI or title is already known | `biorxiv_work_info` | one DOI lookup or a title-substring search across bioRxiv feed batches |
biorxiv_search
Uses an LLM-assisted parsing attempt to turn a natural-language research question into structured OpenAlex filters, then searches OpenAlex. Use this when several filter dimensions must be inferred together or the requested filters are ambiguous. If parsing is unavailable, the original query is sent to OpenAlex without inferred filters. **Parameters:** - query: Natural-language research question. The LLM extracts filter dimensions such as year, citations, institution, author, and journal. - per_page/page: Pagination (default 25, maximum 100 results per page). **Returns:** The same result shape as `search_open_access_works`. **Scholar MCP internal routing:** Every operation named below is exposed by this same Scholar MCP server. | User intent or condition | Scholar MCP operation | Request work | |---|---|---| | Natural-language query that typically needs three or more inferred filter dimensions, or has ambiguous filtering requirements | `smart_open_access_search` | one LLM parsing attempt, then one OpenAlex operation; rate-limit retries may add requests | | Concise topic query with keywords and at most one straightforward filter | `search_open_access_works` | one OpenAlex operation; rate-limit retries may add requests | | User supplies explicit fields and AND/OR logic | `advanced_search` | one OpenAlex operation; rate-limit retries may add requests | **Example for this tool:** "highly cited papers on AI from top universities published after 2020" (citation + institution + date filters combined).
smart_open_access_search
An agentic RAG (Retrieval-Augmented Generation) system for iterative, multi-round knowledge retrieval. ⚠️ CRITICAL: This is NOT a single-call tool. You MUST call it multiple times (up to 20 rounds allowed). **MANDATORY ITERATION PROTOCOL:** 1. Call the tool with your initial query 2. Receive 'passages' and 'should_continue' flag 3. IF 'should_continue' is TRUE → YOU MUST CALL AGAIN WITH A DIFFERENT QUERY - Read and analyze ALL passages to understand what information you got - Identify what's MISSING or unclear from current passages - Generate a COMPLETELY DIFFERENT query from a NEW ANGLE - Call the tool again immediately - Do NOT answer the user's question yet 4. IF 'should_continue' is FALSE → You have enough information to answer **🔥 CRITICAL: Query Diversity Requirements** Each new query MUST be SUBSTANTIALLY DIFFERENT from previous ones to avoid duplicate results: ❌ BAD (too similar): - Round 1: "user book acquisition" - Round 2: "user acquiring books" ← Same concept, will get duplicate results! ✅ GOOD (different angles): - Round 1: "user book acquisition" → general discussion - Round 2: "PDF reader features personalization" → technical features angle - Round 3: "reading behavior patterns analysis" → behavioral angle - Round 4: "book recommendation algorithms" → algorithmic angle **How to generate DIVERSE queries:** 1. **Different aspects**: If Round 1 was about "what", try "how", "why", "when", "who" 2. **Different granularity**: Broad overview → specific details → edge cases 3. **Different perspectives**: User view → system view → business view 4. **Different domains**: Features → behavior → architecture → performance 5. **Complementary info**: If got "benefits", ask about "challenges" or "implementation" **Required analysis before each new query:** Before calling again, you MUST: 1. Summarize key themes from current passages 2. List what topics/angles are MISSING 3. Choose ONE missing angle to explore 4. Formulate query targeting ONLY that new angle 5. Ensure new query uses DIFFERENT keywords than before **Example multi-round with diverse queries:** Round 1: "user book acquisition methods" → Got: General discussion about users getting books ✓ Covered: Basic concepts, user workflows ✗ Missing: Specific features, technical implementation Round 2: "PDF reading features personalization customization" → Got: Feature descriptions, customization options ✓ Covered: Features, UI/UX aspects ✗ Missing: User behavior data, usage patterns Round 3: "reading behavior PDF vs web statistics" → Got: Behavioral comparisons, usage statistics ✓ Covered: User behavior, comparison data ✗ Missing: Technical architecture, system design Round 4: "knowledge base architecture search retrieval" → Got: System design, technical implementation ✓ should_continue = false → NOW comprehensive coverage **REMEMBER:** - Same query = same results = wasted call! - Each query should explore a NEW dimension/angle - Analyze passages content, not just count - should_continue: true = MANDATORY different query - should_continue: false = Stop and answer - more then 5 rounds allowed
wisebase_rag_answer
get file list from Wisebase
wisebase_file_list
upload file to Wisebase
wisebase_upload
Connect your account to use private features.
Check account status without starting login.

FAQs

Sider Scholar ChatGPT Plugin FAQ

How the directory, categories and Discoverability Score work.

Read the methodology

How do I improve Sider Scholar's ChatGPT Plugin discoverability?

The levers are the listing surface agents actually read: names, descriptions, keywords, tool metadata, and registry health. Which lever matters depends on where discovery breaks, which is what continuous measurement shows.

What are Sider Scholar alternatives on ChatGPT?

As of 2026-11-02, Sider Scholar competes with Aarth, AcaTrove, Agentic Search by Liner, AllNutrition, alphaXiv, Anatomy, Article Galaxy, Atlante Clinico and 21 more in ChatGPT Academic Literature Search & Research Assistants, ranked by public Discoverability Score.

Where is this profile measured?

This profile uses the geography attached to the latest public registry snapshot: US. Locale tags are intentionally omitted.