Wikipedia Topic Builder

An MCP server for building comprehensive Wikipedia article lists

This server provides tools that help an AI assistant identify all Wikipedia articles belonging to a topic. It speaks the Model Context Protocol (MCP), so it works with any MCP-compatible client — Claude, ChatGPT, and others. Connect it and have a conversation to build your topic.

The server URL is:

https://topic-builder.wikiedu.org/mcp

No authentication required.

Connect to Claude

Detailed setup for Claude on the web. Choose the setup that matches your account type:

Individual Claude account
1 Open Settings
Go to claude.ai. Click your profile icon (bottom-left), then Settings.
2 Add the integration
Go to the Integrations tab. Click Add More, then Add custom integration. Enter this URL:
https://topic-builder.wikiedu.org/mcp
Name it Wikipedia Topic Builder. Set authentication to None.
3 Start a conversation
Start a new chat. Click the Integrations icon (plug icon) in the message bar and toggle Wikipedia Topic Builder on. Then try:
"I want to build a list of all Wikipedia articles about human trafficking. Let's start with reconnaissance."
Organization account — admin setup

As an org admin, you add the connector once and it becomes available to all members.

1 Open Organization Settings
Go to claude.ai. Click your profile icon, then Settings, then navigate to your organization's admin settings.
2 Add a connector
Find the Connectors section. Click Add Connector. Enter:
https://topic-builder.wikiedu.org/mcp
Name it Wikipedia Topic Builder. Set authentication to None.
3 Done
The connector is now available to all members of your organization. They can enable it from the Connectors menu in any chat.
Organization account — using an enabled connector

Your admin has already added the Wikipedia Topic Builder connector. You just need to enable it in a chat.

1 Start a new chat
Go to claude.ai and start a new conversation.
2 Enable the connector
Click the Connectors menu (plug icon, or look for it below the message input). Find Wikipedia Topic Builder and toggle it on.
3 Start building
Tell Claude what topic you want to explore:
"I want to build a list of all Wikipedia articles about human trafficking. Let's start with reconnaissance."

Connect to ChatGPT

ChatGPT supports remote MCP servers as custom connectors. Availability and menu names vary by plan (Plus / Pro / Business / Enterprise / Edu) and have shifted as OpenAI has rolled out MCP support — if any step below doesn't match your UI, check OpenAI's MCP documentation.

ChatGPT custom connector
1 Enable developer / connector mode
Go to chatgpt.com. Open Settings → Connectors (or Apps & connectors). If custom connectors aren't visible, look under Advanced for a Developer mode toggle and turn it on.
2 Add a custom connector
Click Add custom connector (or Create). Enter:
https://topic-builder.wikiedu.org/mcp
Name it Wikipedia Topic Builder. Set authentication to No authentication. Save.
3 Use it in a chat
Start a new chat. Open the tools / connectors menu in the composer and enable Wikipedia Topic Builder. Then try:
"I want to build a list of all Wikipedia articles about human trafficking. Let's start with reconnaissance."

Note: tool-calling quality depends on the model you pick. For long multi-step topic builds, use a reasoning-capable model.

Other MCP clients

Any MCP-capable client (Cursor, Zed, Continue, custom agents built on the protocol, etc.) can connect to the URL above. Consult your client's documentation for how to add a remote MCP server with no authentication.

What it does

You describe a topic, and the AI uses Wikipedia's APIs to systematically find all relevant articles. The workflow is:

  1. Scope — Discuss how broadly to define the topic
  2. Reconnaissance — Survey how Wikipedia organizes the topic (categories, WikiProjects, index pages)
  3. Gather — Collect candidate articles from multiple strategies
  4. Score & Review — the AI scores articles for relevance; you review borderline cases
  5. Edge Browse — Find articles that structured strategies missed
  6. Export — Download a CSV of the final article list

Topics are saved automatically. You can leave a conversation and come back later to continue where you left off.

Available tools

start_topic / resume_topic
Begin a new topic build or resume an existing one
survey_categories
Survey Wikipedia's category tree for a topic (without collecting articles yet)
check_wikiproject
Check if a WikiProject exists (the best single source of curated articles)
find_list_pages
Search for Index/List/Glossary pages about the topic
get_wikiproject_articles
Fetch all articles tagged by a WikiProject
get_category_articles
Crawl a category tree and collect articles
harvest_list_page
Extract article links from an Index or List page
search_articles
Search Wikipedia using CirrusSearch operators
search_similar
Find articles similar to a given article (great for finding gaps)
score_by_extract
Fetch article introductions for Claude to judge relevance
set_scores
Save relevance scores (1–10) for articles
browse_edges
Find related articles by browsing outgoing links from confirmed articles
remove_by_pattern
Bulk-remove articles matching a pattern (with dry-run preview)
get_status
See current article count, score distribution, source breakdown
get_articles
List articles with optional filters (by score, source, etc.)
filter_articles
Clean up: resolve redirects, remove disambiguation and list pages
export_csv
Export the final article list as a downloadable CSV

Output format

The final CSV has one article title per line, no header — ready for the Wiki Education Impact Visualizer.

Built by Wiki Education. Source: GitHub (coming soon).