searchLABSCO SUMMARY
The 500-character threshold is what makes the fallback useful.
Preferring Simple English would be a liability if it meant getting a two-sentence stub instead of a real article. Checking the length first means you get the clearer version when there is one and the complete version when there is not, and the response tells you which you got. The mode switch is the escape hatch: leave it on simple for explanations and general reading, set it to full when the topic is technical enough that simplification loses the content.
What it is
An MCP server over Wikipedia that prefers Simple English and falls back to regular English when the simple version is missing or too thin. The fallback is quality-based, not just existence-based: if the Simple English article is under 500 characters it is treated as a stub and the English one is fetched instead.
What you get
- A search across Wikipedia returning ranked article titles with metadata, capped by a limit between 1 and 20 that defaults to 10 —
search - A page summary for quick answers, with the title, Wikipedia version, language code, URL and content length in the metadata block —
summary - The complete article text when a summary is not enough, with the same metadata alongside it —
content - Disambiguation handled rather than guessed: when several pages match, the options come back as a list to choose from
- Auto-suggest on titles by default, so a near-miss title still resolves
- Structured responses that separate metadata from content, so the answer says which Wikipedia version and language it actually came from
Requirements
No account and no key — it reads public Wikipedia. Python 3.12 or higher and the uv package manager; run straight from the repository with uvx git+https://github.com/bhubbb/mcp-se-wikipedia, or clone and uv sync. The package is mcp-se-wikipedia (version 0.1.0) over stdio. One environment variable changes the behaviour: WIKIPEDIA_MODE defaults to simple, and setting it to full bypasses Simple English entirely — worth doing when you need technical depth rather than clarity.
Setup effort
One command — uvx git+https://github.com/bhubbb/mcp-se-wikipedia
USE CASES
01
Getting a clear explanation of something unfamiliar
Ask for the summary and let it prefer the Simple English article, which is written for clarity rather than completeness.
02
Checking a fact mid-conversation
Search for the article and read the summary, and see in the metadata which Wikipedia version answered.
03
Reading a whole article for research
Pull the full content rather than the excerpt, with the quality check deciding which language version has the substance.
04
Resolving an ambiguous name
Let the disambiguation options come back as a list and pick the one you meant, instead of getting the wrong Mercury.
05
Working on a technical topic
Set the mode to full so it goes straight to regular English, where the depth actually is.
3 tools
Listed in project docs. Your client may show a different list.
summarycontentBEFORE YOU INSTALL
What to know first
Tools you get
3 tools named in the project's documentation.
Requires
- uvx on PATH
- Python 3.12 or later
Where it runs
Both documented setups run the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
uvx git+https://github.com/bhubbb/mcp-se-wikipediaMCP Clients
Claude Desktop — uvx
CLAUDE DESKTOP — UVX · JSON
{
"mcpServers": {
"wikipedia-se": {
"command": "uvx",
"args": [
"git+https://github.com/bhubbb/mcp-se-wikipedia"
]
}
}
}Claude Desktop — English only
CLAUDE DESKTOP — ENGLISH ONLY · JSON
{
"mcpServers": {
"wikipedia-se": {
"command": "uvx",
"args": [
"git+https://github.com/bhubbb/mcp-se-wikipedia"
],
"env": {
"WIKIPEDIA_MODE": "full"
}
}
}
}
