Bragproof

← Reports

document-mcp

Starts with no setup4.14.230npm

Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.

Needs to start: nothing
Returns a result when called with no setup: 1 of 1 tool tried
Contacts while installing and starting: nothing

21tools listed
0hosts contacted
0files written
0.8 sto start
35dependencies

What it contacted

Nothing besides the npm registry it was installed from. Watched from outside its sandbox while it was installed and started with no input. Its tools may still contact things when called.

Starting it

npx -y document-mcp@4.14.230

Installing a package runs its code. Use a sandbox for anything you have not read.

Calling its tools

1 tool that takes no input and looks read-only was called once with nothing. 1 returned a result.

list_document_conversionsReturned a result under 0.1 s · 8,129 characters

During the calls it contacted nothing it had not already contacted.

Only tools whose names read like looking something up, with no required input, are tried, five at most. Tools that need input, and anything that sounds like it changes or sends something, are not called.

What its tools tell an agent

In the tool descriptions, nothing that talks about the user, other tools or private files, or uses hidden characters.

Found by simple pattern rules in each tool's description (up to 3,000 characters), quoted as written. Parameter descriptions are not scanned. A clean result is not a safety review.

Tools

compute_formula source, bindings
Reads every formula a document embeds (docx/odt/markdown paragraphs and pptx/odp slide shapes; a table cell's own blocks too — docx's own reader recovers a real equation nested inside a table cell; structurally, the walk also covers a drawing page's own shape flow, though no writer in the family populates a formula there today; a spreadsheet's own cell-anchored formula objects; a standalone .odf formula document; and a formula nested inside another embedded object at any depth, e.g. a formula embedded in a drawing embedded in a spreadsheet) and evaluates each through document-compute.js's units-typed evaluate() — a caller's way to check whether a document's stated arithmetic actually checks out. A formula referencing a symbol (e.g. F = m * a) needs that symbol's value supplied via bindings, keyed by the document's own symbol-table id (see the document's symbolTable.symbols[].id, or a returned formula's own latex to identify which symbol is which); a formula with no free symbols (units and numeric literals only) evaluates with no bindings at all. Each formula reports its own outcome independently — 'evaluated' with the result, 'no-content' when the formula was never lowered to a computable MathExpression (the common case for a spreadsheet's own embedded formula object, or any format other than markdown, none of which yet stores the semantic layer on disk), or 'error' naming which document-compute.js error it hit (e.g. UnboundSymbolError) — so one formula needing more bindings never blocks the others. Each entry's own `locate` field is the reliable way to tell two formulas in the same document apart — a structural path guaranteed unique per formula — unlike `sourcePath`, which several formats leave undefined or stamp with the identical constant across sibling formulas (markdown's own display-math lowering among them).
convert_document source, targetFormat, output, fonts, onSubstitutionDiagnostics, images
Converts a document from one supported format to another via documents.js's DocumentConverter port — docx, pptx, xlsx, odt, odp, ods, odg, odf, markdown, rtf, wpd, doc, xls, ppt, epub, csv, svg, and pdf. Not every (source, targetFormat) pair is supported directly (odf, for instance, only ever converts to pdf); call list_document_conversions first to see which pairs actually are.
list_document_conversions
Lists every (source, target) format pair convert_document actually supports, straight from documents.js's own DocumentConverter port — the definitive source of truth for what convert_document will and will not accept as a (source, targetFormat) combination.
docx_extras source
Reads a docx's own comments, footnotes, header/footer parts, and numbering definitions — data documents.js's ContentDocument pivot cannot carry, so ordinary document-reading operations never see it. Returns the real DocxExtras object (comments/footnotes/headerFooterParts/sectionHeaderFooters/numbering) as structured data.
document_create format, output
Creates a fresh, blank document in the given format via documents.js's own live-view editors (createDocx/createOdt/createMarkdownEditor/...), the same construction document_append_paragraphs's own edit calls build on. Returns an empty document with no content — follow with document_append_paragraphs (docx/odt/markdown) to add text.
16 more tools
document_append_paragraphs source, targetFormat, paragraphs, output
Appends one or more paragraphs — each optionally built from several independently-formatted runs — to the end of a docx, odt, or markdown document, through documents.js's own live-view editors (the same DocxBody.appendParagraph/OdtBody.appendParagraph/MarkdownBody.appendParagraph document-cli's own TUI uses). Does not convert format — the source document's own format and targetFormat must match. docx and odt share an identical field set (underline, fontFamily, sizePt, colorHex, headingLevel, alignment all supported); markdown supports a different, smaller set (hyperlink, code) and rejects the docx/odt-only fields outright rather than silently dropping them. This covers wordprocessing paragraph/run editing only — slides, sheets, drawings, tables, lists, and images are a separate, larger editing surface not exposed here yet.
fonts source
Lists every source-embedded font face a docx/pptx/odt/odp/ods/odg document carries (family, weight/style, byte length).
describe_font_file source
Reads a standalone TrueType/OpenType font file (.ttf/.otf) and reports the family/bold/italic triple it declares about itself.
from_package source, targetFormat, output
Rebuilds real document bytes in a target format from a DocumentTree previously serialised to JSON (e.g. by a caller's own --dump-package-equivalent step) — the read side of the DocumentTree round trip a conversion's onDocument callback produces.
metadata_read source
Reads a document's own title/author/subject/keywords/creator/producer/created-and-modified-timestamp metadata. Works across every supported format, including xlsx (read via a throwaway xlsx-to-pdf preview, since documents.js has no dedicated xlsx metadata reader of its own) and odf (a standalone formula document).
metadata_write source, targetFormat, output, setTitle, setAuthor, setSubject, setKeywords
Patches a document's own title/author/subject/keywords, leaving every other field and every other flag as-is. Does not convert format — the source document's own format and targetFormat must match (or both be 'pdf'); odf (a standalone formula document) is rejected outright as either a source or a target, since it has no write path back out at all. Convert the document to a different format first (e.g. with a documents.js conversion operation) if metadata needs to be set on the result of a format change.
odb_tables source
Lists every table an embedded .odb database declares — column names, types, and row data — across every storage tier documents.js supports (HSQLDB TEXT/CACHED/BINARY script formats, Firebird gbak backups).
odb_forms source
Lists every form an .odb database declares, with each form's own data source and field-bound controls.
odb_reports source
Lists every report an .odb database declares, with each report's own data-source command, band/group structure, and rpt: formula expressions.
odb_query source, sql, query
Runs a bounded SELECT (with optional JOINs of any kind, table aliases, a derived table in FROM, and IN/EXISTS subqueries) over an embedded .odb database's own extracted tables, given directly as SQL or by naming one of the database's saved queries. No database engine is involved — the query runs in memory over the same tables odb_tables would return, against a closed grammar (SELECT/FROM/JOIN [INNER|LEFT [OUTER]|RIGHT [OUTER]|FULL [OUTER]|CROSS|NATURAL] ... [ON|USING]/WHERE/GROUP BY/ORDER BY, with an optional [AS] alias on any table, WHERE and ON also accepting [NOT] IN (SELECT ...) and [NOT] EXISTS (SELECT ...) — no column aliases); an unsupported construct is reported as an error naming it, never silently ignored.
odb_to_csv source, table, output
Extracts exactly one named table from an embedded .odb database as CSV bytes. The table name is required whenever the database declares more than one table.
odb_to_xlsx source, output
Extracts every table an embedded .odb database declares into one xlsx workbook, one sheet per table.
odb_render_report source, report, targetFormat, output, fonts
Resolves one of an .odb database's own reports — its data-bound command run through the bounded SQL engine, its rpt: formulas evaluated, its bands laid out — and renders the result to docx, odt, or pdf.
odm_to_pdf source, chapters, chaptersDir, output
Converts a .odm (ODF master document) to PDF. A .odm never carries its own chapters' content inline — every text:section is a bare external reference to a standalone .odt file — so each chapter the master document declares must resolve through `chapters` (an explicit href -> document override) and/or `chaptersDir` (a directory searched by the href's own basename), checked in that order. A chapter left unresolved by both fails the whole conversion, naming every unresolved href.
outline_document source
Projects a document's table of contents as a structured outline: reads the source's own native DocumentTree directly (documents.js's readNativeDocumentTree — no bridging conversion, no discarded output bytes) and runs document-outline.js's buildOutline over it. Groups carry { text, level, children } (a heading's, list item's, slide's, sheet's, or page's own label plus nested children); leaves carry { kind, text }.
pdf_inspect source, full
Parses a PDF (documents.js's readPdf) and reports a summary: page count, each page's own size and item-kind histogram, document metadata, and embedded image formats. Pass full: true to return the entire parsed LayoutDocument instead of a summary.

Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.

Install facts

LicenseMIT
Needsnode >=20
Sourcegithub.com/ExaDev/documents.js
Install scriptsNone declared by it or anything installed with it.
Tarballsha512-qZsmp/bWv7bT2Us53Mpz085ThyTZbfWKiB1Bm5qhvJH3C7tOgVcAV1KnUVCSh0LagIZCd1UaSOGlcLa1QtDgRQ==

Versions reported

VersionRunResultTools
4.14.2302026-11-16Starts with no setup21
4.14.2292026-11-12Starts with no setup21

Check this report yourself

This site did not write the report. A public job on a GitHub-hosted machine did: the run, from this commit of the open-source runner. GitHub signed a token that names that job and the hash of the report, so any edit since would show.

Show it on your README

Bragproof: Starts with no setup

[![Bragproof](https://bragproof.smaverk.com/badge/document-mcp.svg)](https://bragproof.smaverk.com/r/document-mcp)

New version out? Ask for a fresh report.