scopus-mcp
Integrates with the Elsevier Scopus API, with planned Scopus tools and structured response schemas. Currently an initial scaffold supporting MCP initialization and ping.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@scopus-mcp ping the scopus-mcp server to verify it's running"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
scopus-mcp
An MCP server for the Elsevier Scopus API. Runs over stdio with npx and keeps
the API's parameter names and JSON responses.
Quick start
Requires Node.js 22.22.0 or newer, npm, and an MCP client with stdio support. Get an API key from the Elsevier Developer Portal and add this server to your client's configuration:
{
"mcpServers": {
"scopus": {
"command": "npx",
"args": ["-y", "scopus-mcp"],
"env": {
"ELSEVIER_API_KEY": "your-elsevier-api-key"
}
}
}
}Reload the client to connect. To pin a release, use scopus-mcp@<version> in args.
Related MCP server: openrhyme-mcp
Configuration
Environment variable | Description |
| Required for all tools except |
| Institutional token, if provided by your institution. |
Set credentials in the client's env object. The server does not load .env
files. Access to data and views depends on your Elsevier subscription and
institutional access.
The server reports its version in MCP serverInfo and the startup log on stderr.
Tools
Tool | Description |
Find publications. | |
Find authors and co-authors. | |
Find institutions. | |
Get author profiles by ID, EID, or ORCID. | |
Get an institution profile by ID or EID. | |
Get yearly citation counts and summaries. | |
Get publication metrics by identifier. | |
Look up subject codes; no API key needed. |
Each call makes one API request. For additional pages, use the tool's pagination parameters. Requests support cancellation and a 30-second timeout; retries and redirects are not automatic.
Responses and errors
Results follow each tool's outputSchema. The original API JSON is returned in
both structuredContent and a text content block, without reshaping fields or
converting values.
Available quota headers are returned as strings in _meta["scopus-mcp/headers"]:
X-RateLimit-Limit, X-RateLimit-Remaining, X-RateLimit-Reset, and Retry-After.
API failures return isError: true and a JSON text error with code, message,
and, when available, an HTTP status. Credentials are redacted. Invalid arguments
are rejected before an API request.
Error | What to check |
| Set |
HTTP 401 or 403 | Check your key, subscription, institutional network, and token. |
HTTP 429 | Check quota headers and |
| Check connectivity to |
| Elsevier returned invalid JSON or an unexpected response shape. |
API documentation
Development
See Contributing for local setup and changes, and Releases for publishing.
License
MIT © 2026 Andrii Baran. Independent project, not affiliated with Elsevier.
Available Tools
8 toolsaffiliation_retrievalAffiliation RetrievalARead-onlyIdempotent
Retrieve a Scopus institution profile by affiliation_id or eid. Returns the original Elsevier JSON, including profile data or one page of related documents/authors when requested through view. Access depends on entitlements; no linked records or additional pages are fetched automatically.
Inputs: eid, ver, view, field, +4 more. Returns: affiliation-retrieval-response
affiliation_searchAffiliation SearchARead-onlyIdempotent
Search Scopus institution profiles using native affiliation query syntax. Returns one page of native Elsevier JSON, including search-results and pagination. Example: AFFIL(university) AND AFFIL(London). Credentials come from the server environment. Access depends on your Scopus entitlements.
Inputs: query (required), ver, sort, view, +6 more. Returns: Unmodified JSON envelope returned by the Affiliation Search API.
author_retrievalAuthor RetrievalARead-onlyIdempotent
Retrieve Scopus author profiles by author_id, eid, or orcid. Comma-separated author_id or eid values use one native batch request. Returns the original Elsevier JSON; view access depends on entitlements. Pagination and superseded-profile resolution are explicit.
Inputs: eid, ver, view, alias, +6 more. Returns: author-retrieval-response, author-retrieval-response-list
author_searchAuthor SearchARead-onlyIdempotent
Search Scopus author profiles using native queries, or supply co-author to find an author’s collaborators. Returns one page of native Elsevier JSON, including search-results and pagination. Example: AUTHLASTNAME(Smith) AND AUTHFIRST(John). Credentials come from the server environment. Access depends on your Scopus entitlements.
Inputs: ver, sort, view, alias, +8 more. Returns: Unmodified JSON envelope returned by the Author Search API.
citation_overviewCitation OverviewARead-onlyIdempotent
Retrieve yearly citation counts and summaries for Scopus documents. Supply one native document identifier type, with comma-separated values for multiple documents. Returns the original Elsevier JSON in one request. Citation Overview access must be enabled for your API key.
Inputs: doi, pii, ver, date, +10 more. Returns: abstract-citations-response
plumx_metricsPlumX MetricsARead-onlyIdempotent
Retrieve native PlumX metrics for one publication or artifact by identifier. Returns the original Elsevier JSON, including metric categories, count types and sources. Requires active Scopus access. HTTP 404 can mean that no metrics are available or that the identifier is unknown.
Inputs: idType (required), idValue (required), reqId. Returns: id_type, id_value, count_categories
scopus_searchScopus SearchARead-onlyIdempotent
Search Scopus publications with its native query syntax. Returns one page of the original Elsevier JSON, including search-results, entry and pagination. Example: TITLE-ABS-KEY(machine learning) AND PUBYEAR > 2020. Credentials come from the server environment. Access to views and cursor pagination depends on your Scopus entitlements.
Inputs: query (required), ver, date, sort, +11 more. Returns: Unmodified JSON envelope returned by the Scopus Search API.
subject_classificationsScopus Subject ClassificationsARead-onlyIdempotent
Retrieve or filter Scopus subject classifications. Returns the original Elsevier JSON, including subject codes, descriptions, details, and abbreviations. Omit filters to list all classifications. This public endpoint does not require an API key.
Inputs: code, field, abbrev, detail, +1 more. Returns: subject-classifications
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Each tool pairs a distinct entity with a distinct action: author_search/author_retrieval and affiliation_search/affiliation_retrieval are cleanly separated by query-vs-id, and citation_overview, plumx_metrics, scopus_search, and subject_classifications each target unique resources. There is no meaningful overlap that would cause misselection.
Most tools follow a predictable entity_action pattern (author_search, affiliation_retrieval, scopus_search, etc.), which is easy to parse. However, citation_overview, plumx_metrics, and subject_classifications are noun-only with no verb, a minor deviation from the dominant convention.
Eight tools is well-scoped for a Scopus API wrapper, with two search/retrieve pairs for authors and affiliations plus publication search, citations, metrics, and classifications. Each tool earns its place without redundancy.
Coverage is broad: search and retrieval for authors and affiliations, publication search, citation overview, PlumX metrics, and subject classifications. The main gap is a document-level retrieval tool (e.g., fetch a specific publication by DOI/EID), which agents must currently work around.
Maintenance
Related MCP Connectors
Query SEC EDGAR filings, XBRL financials, and company data via MCP. STDIO or Streamable HTTP.
Unified 15-tool SEO, SERP, clean Markdown & GEO (LLM citation Share-of-Voice) MCP server.
MCP server for progressive tool usage at any scale (see https://klavis.ai)
MCP server for Pentest-Tools.com: run scans, manage findings and reports via your preffered LLM.
Related MCP Servers
- AlicenseAqualityDmaintenanceProvides access to the Elsevier Scopus API, enabling AI assistants to search for academic papers, retrieve detailed abstracts, and look up author profiles. It facilitates bibliometric research and scholarly data analysis through natural language commands.5177 PyPI55MIT

openrhyme-mcpofficial
AlicenseAqualityBmaintenanceEnables any MCP-compatible agent to query a local OpenRhyme activity timeline, search history, and issue control commands over stdio while keeping all data on-machine.51MIT- AlicenseAqualityBmaintenanceEnables MCP clients to connect to Agenzax's REST API over stdio, providing tools for messaging, session management, and review-mode oversight.18135 npm5MIT
- AlicenseNot gradedqualityCmaintenanceProvides a runnable local stdio Python server scaffold that coding agents extend into custom tool integrations by describing an idea and letting the agent investigate, build, test, and install it. Ships with no prebuilt tools, so it enables guided, agent-assisted creation of MCP tools connected to external APIs, databases, or websites while writes stay disabled until explicitly agreed.1MIT