Local MCP toolkit for AI agents: OCR, speech recognition, vision, document conversion, and browser automation with self-hosted local runtimes.
lanxiukai/mcp-tools is an MCP server distributed on github, maintained by lanxiukai, tracked here since July 2026. It has shipped 2 releases and exposes 24 tools. Tools include analyze_chart, analyze_image, asr_status, browser_status, classify_eyewear, classify_eyewear_batch, and 18 more. Its composite risk grade is D — an inferred review prompt computed from observed signals, not a verdict.
Reading the source raised one review prompt — dangerous code — each a pattern worth a human look rather than a finding of fault.
Since the previous scan on 2026-09-01: 1 tool added.
full security breakdown →-
analyze_chart -
analyze_image -
asr_status -
browser_status -
classify_eyewear -
classify_eyewear_batch -
extract_text_from_image -
eyewear_batch_status -
fetch_page -
fetch_page_with_engine -
html_to_pdf -
markdown_to_pdf -
ocr_document -
ocr_status -
ocr_submit -
ocr_wait -
pdf_to_text -
screenshot -
svg_to_png -
transcribe_audio
06-13 00:00 07-27 00:00 now
| version | date | src |
|---|---|---|
| v0.11.0 | 2026-08-24 | github |
| v0.10.0 | 2026-08-24 | github |