DocSlicer MCP
DocSlicer MCP is a lightweight, layout-aware document parser that allows AI agents to parse PDFs, DOCX, PPTX, and HTML into queryable structures. It exposes tools like parse, search, read, get_outline, and to_markdown, enabling agents to navigate long documents by heading hierarchy and extract specific sections without loading entire files into context, preserving tables and citations while reducing token usage.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
What you can do with it
- Parse multi-format documents into structured outlines
- Search documents for specific queries within headings
- Read specific sections by heading to save context
- Export documents to markdown for offline use
Source and maintenance
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
https://github.com/DocSlicer/DocSlicer/releases/download/v0.2.5/docslicer-0.2.5.mcpb 0.2.5
{
"version": "0.2.5",
"transport": "stdio",
"fileSha256": "105d15c612b04e2b5c06970d357527669284f341fa6d9c23ee3e97ef60deafcf",
"identifier": "https://github.com/DocSlicer/DocSlicer/releases/download/v0.2.5/docslicer-0.2.5.mcpb",
"registryType": "mcpb",
"environmentVariables": [
{
"name": "DOCSLICER_MCP_ROOT",
"format": "filepath",
"isRequired": true,
"description": "Restrict file sources and outputs to this directory tree. Several may be given, separated by the platform path separator."
},
{
"name": "DOCSLICER_MCP_ALLOW_CLAUDE_DIR",
"default": "1",
"description": "Set to 0 to refuse documents dropped into a Claude chat, which the app copies into its own directory outside DOCSLICER_MCP_ROOT."
},
{
"name": "DOCSLICER_MCP_ALLOW_URLS",
"default": "1",
"description": "Set to 0 to reject http(s) sources and only permit local files."
}
]
}Tools
Reported by the attributed source; not independently observed by Koskamo.
Let your agent find its tools
Find servers like DocSlicer MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.