Wikipedia for Claude, Cursor, ChatGPT & agents

Wikipedia — search article titles + content, fetch the lead-section summary or full article extract, list table of contents and read individual sections, list article images and resolve to hotlinka...

curl -fsSL https://syncorelabs.ai/install.sh | sh

What it does

Wikipedia — search article titles + content, fetch the lead-section summary or full article extract, list table of contents and read individual sections, list article images and resolve to hotlinkable URLs, list article categories, fetch a random article, and list cross-language editions of a given article. Multilingual via per-language API hosts (en / zh / fr / de / ja / es / ...). No auth needed. Use when the user mentions Wikipedia, encyclopedia, look up, article, summary, or wants encyclopedic grounding for a question.

The Wikipedia skill is one of 75+ pre-wired Syncore integrations that any MCP-compatible client — Claude Desktop, Claude Code, Cursor, Windsurf, Codex CLI, and ChatGPT desktop — can call out of the box. You don't configure MCP servers or copy API keys into a JSON file; the Syncore daemon discovers the skill at startup and exposes its tools to whichever AI client is running.

Sample prompts

Once Syncore is installed and Wikipedia is connected, ask your agent something like:

• “Search for articles from Wikipedia.”
• “Get summary from Wikipedia.”
• “Get article from Wikipedia.”

Tools available (10)

• wikipedia__search_articles

  Search article titles + content for a query. Returns a list of matching titles with snippets.

• wikipedia__get_summary

  Fetch the lead-section summary of an article (the gray top box you see on a normal Wikipedia page). Best for one-shot grounding. NOTE: `title` must be the EXACT article title (case-insensitive, but no fuzzy matching). If you only have a vague topic, call search_articles first and pass the top hit's title. The alias `qu

• wikipedia__get_article

  Fetch a fuller article extract (plain-text). Use for deeper grounding when summary is too short. Same exact-title contract as get_summary — `title` (or its `query` alias) must be the canonical article title.

• wikipedia__get_sections

  Return the table of contents for an article (section ids + titles + level), for selective deeper reads.

• wikipedia__get_section

  Fetch one named section's plain text by section id (from get_sections).

• wikipedia__get_images

  List image filenames associated with an article. Use get_image_url for the resolvable CDN url.

• wikipedia__get_image_url

  Resolve a Wikipedia/Wikimedia image filename to a hotlinkable URL.

• wikipedia__get_categories

  List the categories an article belongs to.

• wikipedia__get_random_article

  Return a random article summary. Useful for serendipitous prompting.

• wikipedia__list_languages

  List the language editions of a given article (for cross-lingual lookups).

How to connect

Wikipedia is a no-auth skill — there's nothing to connect. Once Syncore is installed, your agent can call its tools immediately.

1. Run curl -fsSL https://syncorelabs.ai/install.sh | sh on macOS / Linux (or the PowerShell command on Windows).
2. Run syncore login to create your account and a device-bound encryption key.
3. Run syncore update to sync the skill + credentials to every installed AI client.

Pricing

Free at every Syncore tier. Connect your account once at /connect; the OAuth or API-key credential stays encrypted on your machine and syncs to your other devices via the Syncore vault.

See the full Syncore pricing breakdown — Free $0/mo, Pro $29/mo, Ultra $99/mo — on the homepage.