What it does
DocSlicer is an MCP server that works with documents too large to load into an AI model's context in one go. According to the publisher, it reads only the sections relevant to a given question, so the assistant can answer from the parts of a document that matter.
It is suited to situations where a long file must be queried piece by piece rather than read in full, such as asking targeted questions about a lengthy report or manual. The publisher's description is the only information available for this entry, so details on supported formats or how sections are selected are not stated here.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
DocSlicer
Answer questions from documents too large to fit in context, reading only the sections you need.
v0.2.5As shown on registry.modelcontextprotocol.io when we last read it