Skip to content
Agentmart
Submit a tool

DocSlicer

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

Connector by DocSlicer · GitHub account verified by the MCP Registry

IndexedAGPL-3.0Local (stdio)★ 36
Write a review

Install

Works with Claude Code, Codex, VS Code, Claude Desktop, Cursor, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install connector/docslicer-docslicer

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

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

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.

Tools
4 read · 1 write · 0 delete
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Tools by what they do 5

Read from the source code; the running server may list different tools.

Read 4 · Look things up without changing anything.

  • get_outline
  • parse
  • read
  • search

Write 1 · Create, change, send or run things.

  • to_markdown

Secrets and settings it asks for

Other settings (environment variables or headers).

  • DOCSLICER_MCP_ALLOW_CLAUDE_DIR
  • DOCSLICER_MCP_ALLOW_URLS
  • DOCSLICER_MCP_ROOT

Network hosts it talks to 6

  • docslicer.ai · found in code
  • github.com · found in install command, code
  • iso.org · found in code
  • raw.githubusercontent.com · found in code
  • schemas.microsoft.com · found in code
  • schemas.openxmlformats.org · found in code

Files it touches

  • /sys/devices/system/cpu
  • Your home directory (~)
  • Any path the agent passes to its tools

Tools (5)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • get_outlineGet outline

    Re-fetch a parsed document's outline, with per-heading read costs. Use when the outline has scrolled out of your context. Cheap. Args: doc_id: Handle from parse.

  • parseParse document

    Parse a document and return its heading outline. Call this first. Local path or http(s) URL, format detected automatically. A short document returns as `text` — the whole thing, with `is_complete: true`. There is nothing left to fetch: `read` and `search` on it would return only what you are already holding. Answer from it directly. Everything else returns the outline, not the text. Each line carries the tokens `read` would return for that heading — "~48k" is a section to descend into, "~900" one to just read. The figure includes subsections, so a parent never costs less than the children u…

  • readRead sections

    Return the text under one or more headings, chosen from the outline. Pass a heading's text exactly as the outline shows it. A heading includes its subsections, so it returns roughly the tokens the outline printed against it — prefer a subsection when the parent is large. Asking for a heading and one nested under it returns the ancestor alone, since its text already carries the other; the ones folded in are listed back as "already_included". Outline indentation shows nesting. If a heading appears in more than one place, prefix any ancestor with ">" to pick one — "Notes > Revenue". The full c…

  • searchSearch document

    Find where something is discussed. Use when the outline is not enough. Try the outline first; it is faster. Search is for when it does not settle the question: headings that name nothing useful ("Note 14", "Item 7A"), a figure buried in a table no heading mentions, or a section too big to read whole. Returns places, not answers: each hit is a heading to pass to `read`, what reading it costs, and a snippet — a window cut around the match, flagged "snippet_is_partial" when cut from something longer. Usually `read` the heading. Stop at the snippet only when it answers the question alone and de…

  • to_markdownExport to markdown file

    Write the whole document to disk as markdown. Returns a path, not the text. For when the user wants the document as a file rather than an answer drawn from it. Nothing enters your context, so size does not matter. Tables, charts, page markers and structure are preserved. Args: source: File path or URL. Omit if passing doc_id. doc_id: Handle from a previous parse — reuses it instead of parsing again. password: For an encrypted document. Ignored with doc_id. output_path: Where to write it. Absolute paths are used as given; relative paths resolve against the source file'…

Signals

Stars
36
Forks
5
Open issues
1
Weekly downloads
164
Last commit
Sep 1, 2026 (1 month ago)
Last release
Sep 1, 2026 (1 month ago)
Last package publish
Sep 1, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name
io.github.DocSlicer/docslicer
Version
0.2.5
Auth
No auth
Packages
mcpb https://github.com/DocSlicer/DocSlicer/releases/download/v0.2.5/docslicer-0.2.5.mcpbpypi docslicer
License
AGPL-3.0
Repository
github.com/DocSlicer/DocSlicer
Website
docslicer.ai
First seen
Oct 24, 2026
Last checked
Oct 25, 2026
Source
Official MCP Registrygithub-graphql
Cite this page

DocSlicer MCP server. Agent Mart. https://agentmart.dev/connectors/docslicer-docslicer (last updated 2026-10-25)