← DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-markitdown

Microsoft MarkItDown document conversion integration for DeepSeek Harness.

VisionDeveloper ToolsSecurity & PolicySkills & Workflows
0GitHub Stars0ForksUpdated2026-10-26

Install

No clear install command was found in the current repository evidence.

Plugin Overview & Capabilities

AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.

source-grounded
dsh-markitdown integrates Microsoft MarkItDown into DeepSeek Harness without requiring MCP or bundled binaries. It drives a local Python interpreter to convert multi-format files (PDF, Office documents, HTML, images, and audio) into clean Markdown. It exposes dedicated model-facing tools, a preconfigured workflow skill, optional LLM-assisted image descriptions, and strict egress/path validation safeguards.

Key Capabilities

  • markitdown_check tool to probe the configured Python interpreter and MarkItDown installation readiness
  • markitdown_convert tool to convert local files, batch paths (up to 16 items), base64 input, or URLs into Markdown
  • Support for PDF, DOCX/DOC, PPTX/PPT, XLSX/XLS, CSV, JSON, XML, HTML, EPUB, MSG, ZIP archives, images, and audio
  • LLM-assisted conversion to describe embedded Office document images via OpenAI-compatible endpoints
  • Configurable path boundary (allowedRoot), egress IP pinning, and anti-SSRF protections for URL downloads

Useful For

  • Converting PDF and Office documents to Markdown directly inside DeepSeek Harness workflows
  • Extracting tabular and textual data from spreadsheets, presentations, and documents for LLM ingestion
  • Processing batch documents or web articles into clean Markdown without running external MCP servers

Who It Fits

  • DeepSeek Harness users needing document and presentation text extraction
  • Developers and knowledge workers processing multi-format files in autonomous agent sessions

Documented Limitations

  • Requires a local Python environment with the markitdown package pre-installed; does not ship Python binaries
  • Scanned PDFs lacking an embedded text layer yield minimal or empty Markdown text unless external OCR is configured
  • Complex visual document layouts flatten linearly into Markdown
  • URL sources require network egress and follow strict non-private address restrictions by default

DSH Compatibility

Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.

Not tested yetNo runtime compatibility tests have been published yet.

Security Signals

Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.

Dependency Counts

package.json declares 1 runtime, 9 development, 4 peer, and 0 optional dependencies.

info
Dsh Bundle Declared

package.json declares DSH bundle metadata.

info
License Declared

GitHub reports the repository license as MIT.

info
Package Manifest Available

A root package.json was captured and can be inspected by the registry.

info
Source Available

Public GitHub source metadata is available for this registry snapshot.

info

Source & Registry Notes

Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.

Source repository
AlbertZJ/dsh-markitdown
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
d824291 · 2026-10-26

This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.

Repository Activity

GitHub stars
0GitHub stars
Forks
0
Open issues
0
Last commit
2026-10-26
Last release
No release detected
For maintainers

Maintaining this plugin?

This listing is generated from public repository data. If you maintain this project, you can review the information and share this listing with your users if you find it useful.

Add to README
Listed on DSHPlugin.app