Markdown

Point this at a directory of markdown files and you get six tools: full-text search across all docs, section extraction by heading name, table of contents listing, code block discovery with optional language filtering, and frontmatter parsing. It's built for the markdown that lives in your repo but doesn't get indexed anywhere: ADRs, internal wikis, onboarding guides, architecture notes. The filesystem server reads these as plain text, but this one understands structure. Search returns up to 50 results, section extraction stops at the next same-level heading, and code block queries let you filter by language. Works over stdio with npx, no authentication required.