Skip to main content
Glama
research-mcp

research-mcp

by niol-zh

research-mcp

CI License: MIT

An MCP server for academic literature research. It combines a Scopus search with three free, open scholarly APIs so you get abstracts, author metrics and open-access PDFs without needing institutional Scopus entitlements.

What it does

Tool

Data source

Returns

search_scopus

Elsevier Scopus

Documents matching a query (title, DOI, citations, …)

get_abstract_details

Scopus + CrossRef

Metadata + abstract text

get_author_profile

OpenAlex

h-index, citation count, paper count, affiliations, ORCID

get_citing_papers

OpenAlex (default) or Scopus

Papers that cite a given document (forward citations)

get_references

OpenAlex + CrossRef

Papers cited by a given document (backward citations)

assess_relevance

OpenAlex

Abstract, topics, keywords and term overlap for screening papers against a research context

get_pdf_link

Unpaywall

Open-access PDF link for a DOI

get_quota_status

—

Reminder about Scopus API quota

Citation traversal in both directions

get_citing_papers (forward) and get_references (backward) let you walk a citation graph from any starting paper. Both directions rely on OpenAlex, because a free Scopus key can serve neither:

  • backward — view=REF returns 401 AUTHORIZATION_ERROR

  • forward — REFEID() is a restricted search field and returns 400 INVALID_INPUT

OpenAlex covers both for free, with no quota and generally wider recall, so it is the default for each. Pass a DOI and citation traversal costs no Scopus calls at all.

Screening papers for relevance

assess_relevance takes a list of papers and a plain-language research context, and returns the evidence needed to judge each one: the abstract (from OpenAlex, which covers far more papers than CrossRef), scored topics and keywords, and which of your context's terms appear or are missing.

It screens up to 25 papers in a single call, so a whole search_scopus result set can be triaged in one turn instead of one lookup per paper.

It deliberately returns no verdict and no relevance score. The server has no language model; the judgement is left to the model calling the tool, which reads the abstract itself. The lexical_overlap field is a raw word-match signal that ignores synonyms and meaning — useful supporting evidence, not a ranking.

Why the extra APIs?

A free Scopus API key only grants the search endpoint. The Abstract Retrieval (view=FULL) and Author Retrieval endpoints require an institutional subscription and otherwise return 401 AUTHORIZATION_ERROR. To stay useful for everyone, this server falls back to:

  • CrossRef for abstract text (free, no key)

  • OpenAlex for author metrics incl. h-index (free, no key)

  • Unpaywall for legal open-access PDFs (free, no key)

If you do have institutional Scopus access, the Scopus calls simply return richer data.

Related MCP server: Academic Paper MCP HTTP/SSE Server

Requirements

  • Python ≥ 3.10

  • A free Scopus API key — register at dev.elsevier.com

  • Dependencies: only mcp and httpx

Getting an Elsevier (Scopus) API key

The Scopus tools need an Elsevier Developer API key. It's free to register.

Step by step

  1. Create an Elsevier account. Go to dev.elsevier.com and click "I want an API Key". Sign in, or register a free account (the same account works across Elsevier products such as ScienceDirect and Mendeley).

  2. Open the API Key management page. Once signed in, go to dev.elsevier.com/apikey/manage.

  3. Create a new key. Click "Create API Key" and fill in:

    • Label — any name, e.g. research-mcp.

    • Website URL — required by the form but not validated for server use. You can enter http://localhost or your GitHub repo URL.

    • Optionally a CORS domain — leave blank for server-side use.

  4. Accept the agreements. Tick the API Service Agreement and the text & data mining policy, then submit.

  5. Copy the key. A 32-character hexadecimal key appears (e.g. 1a2b3c4d5e6f...). This is your SCOPUS_API_KEY. You can return to the manage page anytime to view or revoke it.

What the free key can and cannot do

Capability

Free key

Notes

search_scopus

✅

Up to ~20,000 requests/week

get_citing_papers

✅

Via the default source="openalex" — free, no quota

Scopus forward citations (REFEID())

❌

Restricted search field → HTTP 400 INVALID_INPUT; needs an institutional subscription

get_references

✅

Uses OpenAlex/CrossRef, not Scopus — no quota at all

assess_relevance

✅

Uses OpenAlex — no quota (unless you pass Scopus IDs)

Scopus full abstract (view=FULL)

❌

Needs institutional subscription → this server falls back to CrossRef

Scopus reference list (view=REF)

❌

Needs institutional subscription → get_references uses OpenAlex

Scopus author retrieval

❌

Needs institutional subscription → this server uses OpenAlex

get_journal_metrics

⚠️

Uses the Serial Title API, which is entitlement-gated. Without it the tool falls back to a local Scimago table

Unlocking full Scopus data (optional)

The richer Scopus endpoints are gated by your institution's subscription, not by the key tier. To use them:

  • Register / use the key from your institution's network. Elsevier binds entitlements to the institutional IP range. Create or first-use the key while on campus Wi-Fi or your university VPN.

  • Alternatively, request an Institutional Token from your library and set it via the X-ELS-Insttoken header (not currently wired into this server — open an issue if you need it).

Without institutional access the server still works fully: abstracts come from CrossRef, author metrics from OpenAlex, and PDFs from Unpaywall.

Quota & fair use

  • Watch your weekly quota — every call returns X-RateLimit-Remaining headers.

  • Don't hammer the API in tight loops; the search tools cap at 25 results per call by design.

  • The key is a secret. Keep it in the env block of your MCP config, never commit it to git (this repo's .gitignore already excludes .env and keys).


Installation

Option A — One-click install (.mcpb bundle, recommended)

Every release ships a research-mcp-vX.Y.Z.mcpb bundle. Download it and double-click, or drag it into Claude Desktop's Settings window. Claude Code and MCP for Windows install it too.

The bundle asks for your Scopus API key and contact email in a form — the key is stored masked, so there is no config file to hand-edit and no environment variable to set.

It carries no Python dependencies: the bundle declares the uv runtime, and the host resolves mcp and httpx at first launch. That keeps it at ~23 KB and platform-independent — vendoring would not work here, because the MCP SDK depends on the compiled pydantic-core, which cannot be bundled portably across macOS, Windows and Linux.

Option B — Claude Code / Claude Desktop, configured by hand (no server needed)

This is the simplest path. The server runs locally as a stdio process — uvx fetches it straight from GitHub, so there is no web server and no tunnel involved.

Add this to your MCP config (~/.claude.json, or the Claude Desktop claude_desktop_config.json):

{
  "mcpServers": {
    "research": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/niol-zh/research-mcp", "research-mcp"],
      "env": {
        "SCOPUS_API_KEY": "your-scopus-api-key",
        "UNPAYWALL_EMAIL": "you@example.com"
      }
    }
  }
}

Restart Claude. That's it — uvx installs mcp + httpx in an isolated environment automatically.

UNPAYWALL_EMAIL is required for the get_pdf_link tool. Unpaywall rejects requests without a real contact email (HTTP 422). Use your own address. All other tools work without it.

Local clone instead of GitHub

If you've cloned the repo and want to run from disk:

{
  "mcpServers": {
    "research": {
      "command": "uvx",
      "args": ["--from", "/path/to/research-mcp", "research-mcp"],
      "env": { "SCOPUS_API_KEY": "your-scopus-api-key" }
    }
  }
}

Option C — Claude Cowork (remote connector, needs an HTTPS URL)

Cowork runs in an isolated cloud VM and cannot reach a local stdio process. It needs the server exposed over HTTPS using the Streamable HTTP transport. The easiest way is a free Cloudflare Quick Tunnel.

You need two pieces running on your machine:

  1. mcp-proxy — wraps the stdio server as a local HTTP server

  2. cloudflared — exposes that local port over a public HTTPS URL

1. Install the helpers

# mcp-proxy comes via uvx, no install needed
# cloudflared:
#   Windows:  download cloudflared.exe from
#             https://github.com/cloudflare/cloudflared/releases/latest
#   macOS:    brew install cloudflared
#   Linux:    see Cloudflare docs

2. Start the HTTP server (terminal 1)

export SCOPUS_API_KEY="your-scopus-api-key"
export UNPAYWALL_EMAIL="you@example.com"

# --with "mcp<2": uvx resolves mcp-proxy in its own environment, so the cap in
# pyproject.toml does not reach it. Without the pin it pulls mcp 2.x, which no
# longer exports request_ctx, and mcp-proxy dies on import.
uvx --with "mcp<2" mcp-proxy --port 8000 --transport streamablehttp \
  -e SCOPUS_API_KEY "$SCOPUS_API_KEY" \
  -- uvx --from git+https://github.com/niol-zh/research-mcp research-mcp

3. Open the tunnel (terminal 2)

cloudflared tunnel --url http://localhost:8000

Cloudflare prints a URL like https://random-words.trycloudflare.com.

4. Add the connector in Cowork

  • Customize → Connectors → Add custom connector

  • Name: Research

  • Remote MCP server URL: https://random-words.trycloudflare.com/mcp (note the /mcp suffix)

⚠️ A Quick Tunnel URL is temporary — it changes every time you restart cloudflared, and both terminals must stay open while you use Cowork. For a stable URL, deploy the server to a host (Railway, Render, Fly.io, a VPS) or use a named Cloudflare Tunnel.

Windows users: the repo includes scripts/start-tunnel.ps1, which starts the server and the tunnel and copies the connector URL to your clipboard (requires uvx and cloudflared on PATH):

$env:SCOPUS_API_KEY = "your-key"
$env:UNPAYWALL_EMAIL = "you@example.com"
./scripts/start-tunnel.ps1

Example

A typical research flow in Claude, chaining several tools in one turn:

You: How influential is Amy Edmondson's work, and can you get me an open-access PDF of a recent open-science paper to read?

1. get_author_profile("Amy Edmondson") → OpenAlex returns disambiguated matches with metrics:

{
  "matches": [
    {
      "openalex_id": "A5003931866",
      "name": "Amy C. Edmondson",
      "h_index": 66,
      "citation_count": 45902,
      "paper_count": 358,
      "i10_index": 132,
      "affiliations": ["Harvard University"],
      "orcid": "0000-0003-4409-913X",
      "url": "https://openalex.org/A5003931866"
    }
  ],
  "note": "Top 3 matches from OpenAlex — verify by name/affiliation."
}

2. get_pdf_link("10.1371/journal.pone.0173664") → Unpaywall finds a gold open-access PDF:

{
  "doi": "10.1371/journal.pone.0173664",
  "oa_pdf_url": "https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0173664&type=printable",
  "oa_status": "gold",
  "source": "publisher",
  "journal_is_oa": true
}

Claude: Amy C. Edmondson (Harvard) has an h-index of 66 across 358 papers with ~45,900 citations — exceptionally influential in organizational behavior. Here is an open-access PDF you can read: [link].

Every tool returns indented JSON, so Claude parses the fields reliably and combines results across calls. A full literature search would add search_scopus (to find papers) and get_abstract_details (Scopus metadata + abstract text from CrossRef).

Development

# install with dev dependencies
uv pip install -e ".[dev]"      # or: pip install -e ".[dev]"

# run the test suite (offline — all HTTP is mocked, no API key needed)
pytest

Tests live in tests/ and mock every external API with httpx.MockTransport, covering result parsing, count clamping, retry/backoff on HTTP 429, quota tracking and error paths.


Tool reference

search_scopus

Param

Type

Default

Description

query

string

—

Scopus query, e.g. TITLE(agile) AND PUBYEAR > 2020

count

int

5

Results to return (max 25)

sort

string

coverDate

coverDate or relevancy

Each result carries issn and e_issn, which feed straight into get_journal_metrics.

get_abstract_details

Param

Type

Description

scopus_id

string

Scopus document ID

get_author_profile

Param

Type

Description

author_name

string

Author's full name, e.g. Amy Edmondson. Returns the top 3 OpenAlex matches — verify by name/affiliation.

get_citing_papers

Forward citations — papers that cite the given document.

Param

Type

Default

Description

scopus_id

string

—

A DOI or OpenAlex work ID (default source), or a Scopus ID

count

int

5

Results to return (max 25)

sort

string

coverDate

coverDate or relevancy (Scopus only)

source

string

openalex

openalex (free, no quota, most-cited first) or scopus

Why OpenAlex is the default: Scopus serves forward citations through the REFEID() search field, which is restricted. On a free key it returns HTTP 400 INVALID_INPUT ("Use of certain field restrictions in the search query is not allowed for this requestor"), so source="scopus" is only useful with an institutional subscription. If you request it anyway, the tool reports that restriction rather than leaking a bare HTTP error.

get_references

Backward citations — papers cited by the given document, most-cited first.

Param

Type

Default

Description

identifier

string

—

DOI, OpenAlex work ID (W…) or Scopus ID

count

int

10

References to return (max 25)

Reference lists come from OpenAlex, falling back to CrossRef when OpenAlex has none. For works with more than 50 references, ranking considers the first 50; total_references always reports the true count.

assess_relevance

Evidence for screening papers against a research context — no verdict, no score.

Param

Type

Description

identifiers

string[]

Up to 25 papers (DOI, OpenAlex ID or Scopus ID)

research_context

string

What you are looking for, e.g. psychological safety in distributed software teams

Returns per paper: title, DOI, year, venue, citation count, abstract, scored topics and keywords, and lexical_overlap (matched_terms, missing_terms, coverage). Identifiers that cannot be resolved are reported under unresolved rather than silently dropped.

Identifiers

get_references and assess_relevance accept a DOI (preferred — free), an OpenAlex work ID, or a Scopus ID. A Scopus ID costs one Scopus call to resolve its DOI first, so pass DOIs when you have them.

Param

Type

Description

doi

string

DOI, e.g. 10.1016/j.tourman.2026.105478

get_journal_metrics

Param

Type

Description

issn

string

Journal ISSN, with or without the hyphen, e.g. 0001-8392

Returns the quartile (Q1–Q4) per subject category, plus CiteScore, SJR and SNIP. A journal usually sits in several categories with different quartiles, so subject_areas is a list; best_quartile gives the strongest one, which is what papers normally cite.

The source field says where the numbers came from — scopus from the live Serial Title API, scimago from the local fallback table. The two differ slightly, so it is worth reporting which one you used.

The Serial Title API needs an entitlement many keys lack. When it is unavailable the tool falls back to a Scimago table you place at research_mcp/data/scimago.csv — see that directory's README for how to obtain it. The Scimago data is licensed CC BY-NC.

Scopus query syntax (quick reference)

Field

Example

Title

TITLE(machine learning)

Author

AUTH(edmondson)

Keywords

KEY(psychological safety)

Year

PUBYEAR > 2020, PUBYEAR = 2023

Affiliation

AFFIL(harvard)

Combined

TITLE(agile) AND KEY(teams) AND PUBYEAR > 2019

Full syntax: Scopus Search Tips.

License

MIT — see LICENSE.

Acknowledgements

Built on the open scholarly infrastructure of CrossRef, OpenAlex and Unpaywall, plus the Elsevier Scopus API.

Available Tools

9 tools
assess_relevanceA

Screen one or more papers against a research context. Returns, per paper, the abstract (from OpenAlex — broader coverage than CrossRef), scored topics and keywords, and which of your context's terms do and do not appear. Use it to triage a whole search result set in one call, then judge relevance yourself: the server deliberately returns evidence, not a verdict or score.

Inputs: identifiers (required), research_context (required).

get_abstract_detailsA

Retrieve metadata for a Scopus document (authors, journal, citations) plus the abstract text from CrossRef when available.

Inputs: scopus_id (required).

get_author_profileA

Look up an author's h-index, citation count, paper count, ORCID and affiliations via OpenAlex. Provide the author's full name; returns the top 3 matches to disambiguate.

Inputs: author_name (required).

get_citing_papersA

Forward citations: papers that CITE a given document, most-cited first. Defaults to OpenAlex (free, no quota, wide coverage, accepts a DOI or OpenAlex ID). source='scopus' uses REFEID(), a restricted field that only works with an institutional Scopus subscription.

Inputs: scopus_id (required), sort, count, source.

get_journal_metricsA

Journal quality metrics for an ISSN: the quartile (Q1-Q4) per subject category, plus CiteScore, SJR and SNIP. Uses the Scopus Serial Title API and falls back to the bundled Scimago table when that is unavailable. Get an ISSN from search_scopus or get_abstract_details.

Inputs: issn (required).

get_quota_statusA

Report the Scopus API rate-limit (weekly quota) from the most recent response headers. Returns a note if no Scopus call has been made yet.

Inputs: no named parameters.

get_referencesA

Backward citations: the works a given paper CITES (its reference list), via OpenAlex with a CrossRef fallback. Free and does not consume Scopus quota — Scopus itself cannot serve reference lists without an institutional subscription. Returns the most-cited references first.

Inputs: identifier (required), count.

search_scopusA

Search for documents in Scopus by query string. Returns title, DOI, Scopus ID, citation count and journal for each match.

Inputs: query (required), sort, count.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.1/5.0

    Scored across 9 tools

    Disambiguation4/5

    Purposes are largely distinct: search vs. citation graph (backward/forward) vs. author vs. journal metrics vs. PDF lookup are cleanly separated, and get_references vs. get_citing_papers are explicitly contrasted. The only mild overlap is that both assess_relevance and get_abstract_details return abstract text, which could confuse an agent wanting just an abstract.

    Naming Consistency5/5

    Consistent snake_case verb_noun pattern throughout (get_abstract_details, get_author_profile, get_journal_metrics, get_citing_papers, etc.). The two non-'get' verbs (search_scopus, assess_relevance) still follow the same verb_noun convention and read naturally.

    Tool Count5/5

    Nine tools is well-scoped for a literature-research workflow, with no redundant or trivial entries. Each tool (search, metadata, citations, author, journal metrics, PDF, relevance, quota) earns its place.

    Completeness4/5

    Covers the core research-discovery lifecycle: search, metadata/abstracts, backward and forward citations, author profiles, journal quality, OA PDF, and relevance triage, plus a quota utility. Minor gaps exist around saving/exporting results or citation formatting, but nothing that blocks typical workflows.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      A MCP server for academic literature retrieval, aggregating multiple data sources like arXiv, Crossref, OpenAlex, PubMed, and Semantic Scholar to provide search, details, citations, trends, and recommendations.
      4
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      An MCP server that integrates Scopus, Crossref, and PubMed APIs to search academic papers and fetch abstracts, usable with any MCP-compatible AI client.
      2
      MIT