io.github.DocSlicer/docslicerfiles

DocSlicer

Verified · today

Answer questions from documents too large to fit in context, reading only the sections you need.

Install

claude mcp add docslicer -- uvx docslicer

Requires: DOCSLICER_MCP_ROOT, DOCSLICER_MCP_ALLOW_URLS

Our take

A document-questioning server built to handle files that are too large for a single context window by selectively reading relevant sections. It is aimed at research, legal, policy, or enterprise document workflows where targeted retrieval matters more than full ingestion. Packaging across MCPB and PyPI is a decent maturity signal, though adoption still looks early.

reviewed by hand · 2026-08-11

Something wrong or dead here? Report it

Verification record

last verified
today
github stars
14
last commit
yesterday
archived
no
license
AGPL-3.0
in registry since
2026-08-10

github.com/DocSlicer/DocSlicer

ai-netcafefiles

ai-netcafe

Verified · 12 days ago

23 agent tools + a measured per-call model cost dataset. No key needed to start.

hand-reviewed89k starschecked 12 days ago

mcp-serverfiles

mcp-server

Verified · yesterday

Puter MCP enables AI tools to interact with Puter: manage files, websites, workers, and more

hand-reviewed43k starschecked yesterday

mcp-server-filesystemfiles

mcp-server-filesystem

Verified · 18 days ago

MCP server for filesystem access

hand-reviewed38k stars417 dl/wkchecked 18 days ago

desktop-commanderfiles

Desktop Commander

Verified · today

MCP server for terminal commands, file operations, and process management

hand-reviewed9.3k stars110k dl/wkchecked today

basic-memoryfiles

basic-memory

Verified · 5 days ago

Local-first knowledge management with bi-directional LLM sync via Markdown files.

hand-reviewed3.6k starschecked 5 days ago

pdf-reader-mcpfiles

PDF Reader MCP

Verified · 14 days ago

Evidence-first PDF MCP. Agent Document Twin with citeable page+bbox evidence.

hand-reviewed839 stars9.7k dl/wkchecked 14 days ago