About Scite
Evidence-based answers grounded in research
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
Endpoint
https://api.scite.ai/mcpCopy install command
Claude CodeTerminal
claude mcp add --transport http scite https://api.scite.ai/mcpCursor.cursor/mcp.json
{"mcpServers":{"scite":{"type":"http","url":"https://api.scite.ai/mcp"}}}Open in CursorVS Code.vscode/mcp.json
{"servers":{"scite":{"type":"http","url":"https://api.scite.ai/mcp"}}}Open in VS CodeClaude Desktopclaude_desktop_config.json
{"mcpServers":{"scite":{"type":"http","url":"https://api.scite.ai/mcp"}}}Windsurf~/.codeium/windsurf/mcp_config.json
{"mcpServers":{"scite":{"serverUrl":"https://api.scite.ai/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
25| Parameter | Type | Required | Description |
|---|---|---|---|
| term | string | No | Cross-field search query. Optional when `dois` or `titles` is provided (omit to fetch metadata only). IMPORTANT: Use domain-specific technical terms, not broad phrases — the index covers all academic fields so ambiguous terms return irrelevant results. Supports Boolean operators (AND, OR, NOT), phrase search ("exact phrase"), proximity search ("term1 term2"~5). Searches across title, abstract, and full-text. Example: "PAC learning" AND "generalization bounds" AND "neural networks" |
| dois | array | No | Filter results to specific DOIs. Use WITHOUT `term` to fetch paper metadata (title, abstract, citations, access URL). Use WITH `term` to search within those papers for full-text excerpts. Prefer DOIs over titles as they are exact matches. Example: ['10.1038/s41586-020-2649-2']. |
| titles | array | No | Filter results to papers matching these titles. Use WITHOUT `term` to fetch paper metadata, or WITH `term` to search within those papers. Use when DOIs are not available — prefer `dois` when possible. Example: ['Attention is all you need']. |
| limit | integer | No | Maximum number of results to return. Default: 10, Maximum: 1000. For better performance, use smaller limits (10-50) and pagination. |
| offset | integer | No | Pagination offset for result sets. Use with limit for pagination. Example: offset=20, limit=10 returns results 21-30. |
| title | string | No | Filter by text in publication title. Example: 'climate change' |
| abstract | string | No | Filter by text in publication abstract. Example: 'neural networks' |
| author | string | No | Filter by author name. Partial names work. Example: 'Einstein' or 'Albert Einstein' |
| journal | string | No | Filter by journal name. Example: 'Nature' or 'Science' |
| publisher | string | No | Filter by publisher name. Example: 'Elsevier' or 'Springer' |
| year | integer | No | Filter by specific publication year. Example: 2020. Cannot be combined with date_from/date_to. |
| date_from | string | No | Filter papers published from this date onwards. Format: YYYY-MM-DD or YYYY. Example: '2015-01-01' or '2015' |
| date_to | string | No | Filter papers published up to this date. Format: YYYY-MM-DD or YYYY. Example: '2023-12-31' or '2023' |
| paper_type | string | No | Filter by publication type. Examples: 'Article', 'Review', 'Clinical Trial', 'Meta-Analysis', 'Case Report' |
| affiliation | string | No | Filter by author institutional affiliation. Example: 'Stanford University' or 'MIT' |
| topic | string | No | Filter by research topic/subject area. Example: 'Oncology' or 'Neuroscience' |
| has_tally | boolean | No | Filter papers with Smart Citations (tally > 0). true = papers that have been cited with context |
| has_retraction | boolean | No | Filter papers with retraction notices. true = retracted papers only |
| has_concern | boolean | No | Filter papers with editorial concerns. true = papers with concerns |
| has_correction | boolean | No | Filter papers with corrections. true = papers with published corrections |
| has_erratum | boolean | No | Filter papers with errata. true = papers with published errata |
| supporting_from | integer | No | Minimum number of supporting Smart Citations. Example: 10 = papers with at least 10 supporting citations |
| supporting_to | integer | No | Maximum number of supporting Smart Citations. Example: 100 = papers with up to 100 supporting citations |
| contrasting_from | integer | No | Minimum number of contrasting Smart Citations. Example: 5 = papers with at least 5 contrasting citations |
| contrasting_to | integer | No | Maximum number of contrasting Smart Citations. Example: 20 = papers with up to 20 contrasting citations |
| mentioning_from | integer | No | Minimum number of mentioning Smart Citations. Example: 50 = papers with at least 50 mentioning citations |
| mentioning_to | integer | No | Maximum number of mentioning Smart Citations |
| citing_publications_from | integer | No | Minimum number of total citing publications (traditional citation count) |
| citing_publications_to | integer | No | Maximum number of total citing publications (traditional citation count) |
| collection_slug | string | No | Restrict the search to the papers in one of the user's Collections (a saved, named set of papers). Pass the Collection slug from `create_collection` or `search_collections`. Combine with `term` and other filters to search within that Collection. |
Details
The maintainer has not added details yet. Check the README in the repository.
Comments
Markdown supported
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.