wikicitation-mcp

Wikipedia citation-science tools for Claude — pure Python, no R required.

An MCP server that exposes 38 tools to Claude Code, Claude Desktop, and claude.ai.
Ask Claude to fetch Wikipedia edit histories, analyse citations, score scientific quality, and annotate DOIs and ISBNs — all without leaving the chat.

---

What you can do

Category	Examples
Edit history	Full revision history, first/latest wikitext, category-wide sweeps
Citation analysis	Count DOIs/refs/ISBNs, extract CS1 templates, compute SciScore
DOI & ISBN annotation	Enrich DOIs via CrossRef / EuropePMC, fetch BibTeX; books via Open Library / Google Books
Multilingual	Every article-level tool takes lang (en, fr, de, es, it, pt citation templates are recognised natively)

---

Installation

Option A — PyPI (recommended)

No clone needed. uvx downloads and runs the package in one step:

# Requires uv (https://docs.astral.sh/uv/)
uvx wikicitation-mcp

Or install permanently with pip:

pip install wikicitation-mcp
wikicitation-mcp          # starts the stdio server

Option B — From source

git clone https://github.com/jsobel1/wikicitation-mcp.git
cd wikicitation-mcp
uv sync
uv run python server.py

---

Connect to Claude

Claude Code (CLI) — PyPI

claude mcp add wikicitation -- uvx wikicitation-mcp
claude mcp list

Claude Code (CLI) — from source

# Run from inside the cloned directory
claude mcp add wikicitation -- uv run python server.py

Claude Desktop — PyPI

Edit ~/.claude/claude_desktop_config.json (Windows: %APPDATA%\Claude\claude_desktop_config.json):

{
  "mcpServers": {
    "wikicitation": {
      "command": "uvx",
      "args": ["wikicitation-mcp"]
    }
  }
}

Claude Desktop — from source

{
  "mcpServers": {
    "wikicitation": {
      "command": "uv",
      "args": [
        "run", "python",
        "/ABSOLUTE/PATH/TO/wikicitation-mcp/server.py"
      ],
      "cwd": "/ABSOLUTE/PATH/TO/wikicitation-mcp"
    }
  }
}

Restart Claude Desktop — the wikicitation server appears in the toolbar.

claude.ai (web, HTTP transport)

uvx wikicitation-mcp --transport streamable-http --port 8000
# (from a clone: uv run python server.py --transport streamable-http --port 8000)
# Then in claude.ai → Settings → Connections → Add MCP server
# URL: http://localhost:8000/mcp

---

Quick start

Once connected, try these prompts in Claude:

Fetch all edits to the Wikipedia article "Circadian clock" up to today.

Count all DOIs, references, and ISBNs in this wikitext: [paste wikitext]

Calculate the SciScore for "Sleep deprivation".

Extract all citations from "CRISPR" — how many are journals vs websites vs books?

Show me the top 20 most-cited papers in the Wikipedia article "mRNA vaccine".

Annotate these DOIs with CrossRef metadata:
10.1038/nature12373, 10.1016/j.cell.2020.01.001

---

Usage notes

date_limit is an upper bound

date_limit controls the newest revision returned, not the oldest. It defaults to now. To retrieve edits "since 2023", leave it unset and filter the returned rows by timestamp. A plain date (2024-01-01) means the end of that day (UTC).

Languages

Article-level tools accept lang (default "en"), e.g. lang="fr". Citation templates are recognised natively for en, fr, de, es, it and pt, and mapped to the same canonical types so SciScore is comparable across editions.

SciScore

get_sci_score returns sci_score = journal citations ÷ total citation templates, from 0 to 1. Higher means more scientifically sourced.

Optional environment variables

Variable	Effect
GOOGLE_BOOKS_API_KEY	Gives annotate_isbn_google its own quota. Without it, Google often answers HTTP 429; annotate_isbn_openlib needs no key.
CROSSREF_MAILTO	Your e-mail address, sent to CrossRef's polite pool.

Input limits

Arguments are validated before any network call: up to 100 articles, 20 categories and 200 DOIs per call, regular expressions up to 500 characters, text up to 5 million characters, subcategory depth 1–5, and lang must look like a Wikipedia language code.

---

Tool reference

Group 1 — History & metadata (14 tools)

Tool	Key arguments	Returns
get_article_history	article_name, date_limit	revision table (revid, user, timestamp, size, comment)
get_article_recent	article_name, date_limit	metadata + full wikitext
get_article_initial	article_name	first-ever revision metadata + wikitext
get_article_info	article_name	pageid, title, byte length (missing: true if absent)
get_tables_all	article_name, date_limit	initial + recent + history + info in one call
get_category_pages	category	list of article titles
get_pages_in_cat_table	category	structured page table (pageid, title, type)
get_subcat_table	catname, replacement	direct subcategories
get_subcat_multiple	catname_list	subcategories for N categories
get_subcat_with_depth	catname, depth, replacement	recursive subcategories
get_page_in_cat_multiple	catname_list	pages for N categories
get_category_history	article_list	revision table for a list of articles
get_category_recent	article_list, date_limit	metadata + wikitext for a list of articles
get_category_creation	article_list	creation-revision metadata for a list of articles

Group 2 — Citation counting, extraction & quality (19 tools)

Tool	Key arguments	Returns
get_doi_count	text	{"count": N}
get_ref_count	text	{"count": N}
get_url_count	text	{"count": N}
get_isbn_count	text	{"count": N}
get_hyperlink_count	text	{"count": N}
get_any_count	text, regexp	{"count": N}
extract_citations	text	list of CS1 template strings
extract_wikihypelinks	text	list of [[...]] wikilink strings
replace_wikihypelinks	text	{"cleaned_text": ...} with links replaced by display text
parse_cite_type	text	{"cite_type": ..., "fields": {...}}
extract_with_regex	article_name, regexp, date_limit	list of regex matches from live article
extract_all_regex	article_name, date_limit	all built-in pattern matches (doi, url, isbn, pmid, …)
parse_citations	article_name, date_limit	structured citation rows (cite_type, doi, author, year, title)
parse_all_citations	article_name, date_limit	long-form table: one row per citation field
get_citation_types	article_name, date_limit	citation counts by CS1 type
get_source_type_counts	text	citation counts by CS1 type from raw wikitext
get_sci_score	article_name, date_limit	sci_score (see above)
get_top_cited_papers	article_name, date_limit	top 40 DOIs annotated via EuropePMC
get_revert_counts	start, end	revert-tagged edit counts by article (defaults to the last 7 days; ≤30-day window; can take a minute)

Group 3 — DOI & ISBN annotation (5 tools)

Tool	Key arguments	Returns
annotate_dois_europmc	doi_list	title, journal, year, citation_count, is_open_access, PMID/PMCID
annotate_dois_crossref	doi_list	title, authors, journal, year, publisher, citation count
annotate_dois_bibtex	doi_list	{"bibtex_entries": [...]}
annotate_isbn_google	isbn	title, authors, publisher, publishedDate, description (see GOOGLE_BOOKS_API_KEY)
annotate_isbn_openlib	isbn	title, authors, publishers, publish_date, page count

---

Running tests

uv sync --dev
uv run pytest                              # unit tests, no network
uv run pytest --run-integration            # adds live API tests

Integration tests call public APIs (Wikipedia, EuropePMC, CrossRef, Open Library, Google Books) and are skipped by default.

---

Troubleshooting

uvx: command not found

Install uv first:

# macOS / Linux
curl -LsSf https://astral.sh/uv/install.sh | sh

# Windows (PowerShell)
powershell -ExecutionPolicy Bypass -c "irm https://astral.sh/uv/install.ps1 | iex"

Server not appearing in Claude Code

claude mcp remove wikicitation
claude mcp add wikicitation -- uvx wikicitation-mcp
claude mcp list

ModuleNotFoundError: No module named 'mwparserfromhell'

The venv is missing a dependency. Run uv sync inside the cloned repo, or reinstall via pip install wikicitation-mcp.

get_revert_counts returns no results

The Wikipedia recentchanges API only retains ~30 days of history. Requests for date ranges older than that will return empty results.

---

Citing

If you use wikicitation-mcp in research, please cite it using CITATION.cff (GitHub's "Cite this repository" button) or the paper in paper/.

Related projects

These three projects share the same core analysis logic at three different levels of interactivity — pick the one that matches how you want to work.

Project	Interface	When to use
wikicitation-mcp (this repo)	MCP server for Claude Desktop / Claude Code / claude.ai	You want to ask Claude questions in natural language and have it call the tools for you. Pure Python, no R required.
wikilite	R package	You want a programmable pipeline in R / R Markdown / Quarto with full access to revision tables, citation parsers, and ggplot2 / plotly / visNetwork output.
wikiliteApp	Shiny web app (built on wikilite)	You want a point-and-click GUI: per-article tabs (History Flow, Citations, Authorship, Stability with SciScore-over-time, Vandalism & Wars, WikiWho-powered Revision Inspector) and a Corpus Analysis mode (multi-corpus timeline, per-article + per-corpus SciScore, co-citation / publication / wikilink networks, batched EuropePMC + Google Books annotation, multi-sheet XLSX exports).

External references

• Model Context Protocol — MCP specification
• FastMCP — Python MCP framework used here
• mwparserfromhell — wikitext parser