Labsco
vitos73 logo

Xwiki MCP

โ˜… 4

from vitos73

MCP server for XWiki REST API โ€” read your wiki from Claude and other AI agents

๐Ÿ”ฅ๐Ÿ”ฅ๐Ÿ”ฅโœ“ VerifiedAccount requiredAdvanced setup

xwiki-mcp

npm downloads

MCP server for XWiki REST API. Lets AI agents (Claude Code, Claude Desktop, etc.) search, read and write your wiki โ€” with proper Solr full-text search, not the half-broken legacy endpoint most clients default to.

Why this one

Most XWiki MCP servers (including ones generated by AI coding tools) wire up /rest/wikis/{wiki}/search. That endpoint is HQL-based and effectively searches page names only โ€” so a query like "visibility metric" returns nothing if no page is literally named that, even when dozens of pages discuss the topic. xwiki-mcp defaults to /rest/wikis/query?type=solr, which is Solr-backed and indexes actual content with proper relevance ranking.

Tools

Read

ToolDescription
searchFull-text search (Solr by default, legacy fallback). Returns ranked results.
list_spacesList all spaces in the wiki
list_pagesList pages in a space (paginated)
get_pageGet page content and metadata
get_page_childrenList child pages
get_attachmentsList attachments on a page

Write (v0.2+)

ToolDescription
create_pageCreate or update a page (upsert via PUT). XML-safe escaping.
delete_pageDelete a page
add_commentAdd a comment to a page

Search syntax

Solr engine (default) supports:

  • bare terms โ€” full-text match across title (boosted) + content
  • "exact phrase" โ€” phrase match
  • title:foo / name:bar โ€” restrict to a field
  • AND, OR, NOT โ€” boolean operators
  • per-call space:"Parent.Child" parameter narrows results to one space tree

If Solr isn't indexed on your instance, pass engine: "legacy" to fall back to the HQL endpoint.

Development

npm run dev    # tsx, no build step
npm run build  # compile to dist/
npm test       # vitest