Qizhixi MCP 0.1.0

Four tools: parse_document, analyze_image, create_chart, export_report.
DOCX/PDF extraction and local Chinese OCR preserve source locations and return
unverified candidates. Charts consume explicit supplied data; reports contain
editable text, images and sources. Existing Excel calculations remain separate.

Run: qizhixi-mcp --transport stdio
STDIO sends PNG image content and embedded DOCX/JSON resources. Client support
must be verified; resource URIs are not web download links.

HTTP: set a random QZX_API_TOKEN of at least 32 characters, then run
qizhixi-mcp --transport http --host 127.0.0.1 --port 8765
Remote file retrieval is disabled unless QZX_FILE_URL_HOSTS is configured.

The full project contains DEPLOYMENT.txt, HOSTED_PLAN.txt, tests and acceptance
evidence. Official Xfyun deployment is pending; local tests do not certify cloud
installation, platform attachment access or user-visible file downloads.

Linux OCR currently requires libGL.so.1 and libglib-2.0.so.0 through OpenCV.
Bundled Noto CJK font is redistributed under the included SIL OFL license.
