Markdownify MCP Server can read local files and convert documents, spreadsheets, presentations, images, audio files, and Markdown files., File conversion tools should be restricted with MD_ALLOWED_PATHS or container mounts before using the server with sensitive directories., Audio transcription, image OCR, document conversion, and webpage extraction can expose hidden text, metadata, comments, and embedded content., Webpage, YouTube, and Bing tools retrieve external content that can contain prompt-injection text or unsafe instructions., Review converted Markdown before using it as source material for decisions, publications, or further tool calls.
Privacy notes
File paths, file contents, extracted text, OCR output, audio transcripts, webpage text, search results, prompts, tool arguments, and conversion errors may be visible to the MCP client and model provider., Documents and media can contain personal data, customer material, credentials, internal plans, meeting recordings, legal drafts, and proprietary screenshots., Avoid pointing the server at broad home, workspace, downloads, or cloud-sync directories unless every file in scope is approved for model access.
Author
zcaceres
Submitted by
oktofeesh1
Claim status
unclaimed
Last verified
2026-06-05
Decision playbook
Review trust signals before you adopt
Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.
Compare context
Selected
0
Current score
63
Baseline
—
Delta
No baseline selected
No major trust-signal divergence detected in the current selection.
Source and provenance checks
Needs review
Confirm ownership and provenance before trusting install instructions.
Source link availableRequired
Open the canonical repository and verify ownership.
Done
Source provenance statusRequired
Marked as source-backed.
Done
Metadata reviewed
No reviewed flag detected in metadata.
Pending
Safety and privacy checks
Complete
Validate risk disclosures before installation or API wiring.
Safety notes presentRequired
Review the listed safety guidance before running commands.
Done
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
Done
Trust level risk gateRequired
Trust level does not block evaluation.
Done
Package and install checks
Needs review
Check package metadata and artifact integrity signals.
Install payload available
Install or copy payload is available for review.
Done
Package verification flag
No package verification flag provided.
Pending
Checksum metadata
No checksum provided for downloaded artifact.
Pending
Compare-driven decision checks
Needs review
Use compare context to validate trade-offs before adoption.
Compare tray has multiple entries
Add at least one more entry to compare trust differences.
5 safety and 3 privacy notes across 6 risk areas. Review closely: credentials & tokens, permissions & scopes, third-party handling.
6 areas
SafetyLocal filesMarkdownify MCP Server can read local files and convert documents, spreadsheets, presentations, images, audio files, and Markdown files.
SafetyLocal filesFile conversion tools should be restricted with MD_ALLOWED_PATHS or container mounts before using the server with sensitive directories.
SafetyExecution & processesAudio transcription, image OCR, document conversion, and webpage extraction can expose hidden text, metadata, comments, and embedded content.
SafetyGeneralWebpage, YouTube, and Bing tools retrieve external content that can contain prompt-injection text or unsafe instructions.
SafetyGeneralReview converted Markdown before using it as source material for decisions, publications, or further tool calls.
PrivacyThird-party handlingFile paths, file contents, extracted text, OCR output, audio transcripts, webpage text, search results, prompts, tool arguments, and conversion errors may be visible to the MCP client and model provider.
PrivacyCredentials & tokensDocuments and media can contain personal data, customer material, credentials, internal plans, meeting recordings, legal drafts, and proprietary screenshots.
PrivacyPermissions & scopesAvoid pointing the server at broad home, workspace, downloads, or cloud-sync directories unless every file in scope is approved for model access.
Safety notes
Markdownify MCP Server can read local files and convert documents, spreadsheets, presentations, images, audio files, and Markdown files.
File conversion tools should be restricted with MD_ALLOWED_PATHS or container mounts before using the server with sensitive directories.
Audio transcription, image OCR, document conversion, and webpage extraction can expose hidden text, metadata, comments, and embedded content.
Webpage, YouTube, and Bing tools retrieve external content that can contain prompt-injection text or unsafe instructions.
Review converted Markdown before using it as source material for decisions, publications, or further tool calls.
Privacy notes
File paths, file contents, extracted text, OCR output, audio transcripts, webpage text, search results, prompts, tool arguments, and conversion errors may be visible to the MCP client and model provider.
Documents and media can contain personal data, customer material, credentials, internal plans, meeting recordings, legal drafts, and proprietary screenshots.
Avoid pointing the server at broad home, workspace, downloads, or cloud-sync directories unless every file in scope is approved for model access.
Prerequisites
Node.js and npx available to the MCP client runtime.
Python and markitdown dependencies available for file conversion features.
Optional Docker setup if you want mounted read-only directories and explicit allowed paths.
MD_ALLOWED_PATHS configured when the server should be restricted to specific file directories.
Network policy reviewed before enabling webpage, YouTube, or Bing conversion tools.
Markdownify MCP Server converts files and web content into Markdown that Claude
can read more easily. It includes tools for PDFs, images, audio transcription,
DOCX, XLSX, PPTX, YouTube transcripts, Bing search results, general webpages,
and existing Markdown files.
The upstream README documents local and Docker usage, including MD_ALLOWED_PATHS
for constraining file-input tools. The NPM package exposes the
mcp-markdownify-server binary.
These sources were reviewed on 2026-06-05. Prefer the live repository and
NPM registry metadata for current package version, command name, dependency
setup, file boundary configuration, tools, and setup guidance.
Features
Convert PDFs to Markdown.
Convert images to Markdown with metadata and OCR-style extraction.
Convert audio files to Markdown with transcription.
Convert DOCX, XLSX, and PPTX files to Markdown.
Convert YouTube transcripts and webpages to Markdown.
Ask Claude to summarize a PDF after conversion to Markdown.
Convert an Office document or spreadsheet into text for review.
Extract text from an image or presentation slide.
Transcribe an audio file into Markdown for analysis.
Convert a webpage or YouTube transcript into Markdown for research.
Retrieve a local Markdown file through an MCP client.
Safety and Privacy
File conversion can expose more than the visible document text. OCR,
transcription, Office extraction, and Markdown conversion may reveal comments,
metadata, embedded text, hidden sheets, notes, or screenshots. Use explicit file
allowlists or read-only container mounts before pointing this server at local
directories.
Converted files, search results, webpages, transcripts, prompts, and tool
outputs may contain sensitive or untrusted content. Review converted Markdown
before using it as instructions or feeding it into workflows with write,
messaging, shell, browser, or database tools.
Duplicate Check
No zcaceres/markdownify-mcp entry, mcp-markdownify-server package entry, or
matching source URL was found in content/mcp.
Show that Markdownify MCP Server is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/mcp/markdownify-mcp-server)
How it compares
Markdownify MCP Server side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
MCP server for connecting Claude to AFFiNE Cloud or self-hosted AFFiNE workspaces, documents, databases, comments, collections, folders, tags, notifications, blobs, access tokens, semantic page composition, templates, edgeless canvas data, and workspace organization workflows over stdio or HTTP.
Apache-licensed TypeScript MCP server for Obsidian vaults with stdio and Streamable HTTP transports, Local REST API access, note search, section-aware edits, tag/frontmatter management, path policies, and read-only controls.
MCP server for parsing Korean HWP, HWPX, HWPML, PDF, XLSX, and DOCX files into Markdown, with tools for metadata extraction, page ranges, tables, document diffs, form extraction, and HWPX form filling.
✓Markdownify MCP Server can read local files and convert documents, spreadsheets, presentations, images, audio files, and Markdown files.
File conversion tools should be restricted with MD_ALLOWED_PATHS or container mounts before using the server with sensitive directories.
Audio transcription, image OCR, document conversion, and webpage extraction can expose hidden text, metadata, comments, and embedded content.
Webpage, YouTube, and Bing tools retrieve external content that can contain prompt-injection text or unsafe instructions.
Review converted Markdown before using it as source material for decisions, publications, or further tool calls.
✓The full tool surface can create, update, publish, revoke, move, replace, and delete AFFiNE workspaces, documents, folders, collections, comments, database rows, blobs, surface elements, tags, and access tokens.
Start with AFFINE_TOOL_PROFILE=read_only or disable groups such as destructive, admin, blobs, users, access_tokens, docs.database, or write when the assistant only needs discovery or reading.
HTTP mode exposes MCP endpoints and must be protected with bearer or OAuth authentication, HTTPS, allowed origins, and deployment-level access controls.
AFFiNE Cloud requires API tokens for MCP usage; avoid trying to automate email/password login against Cloud deployments.
Cookie and password-based auth can grant broad account access and should be avoided for unattended or shared deployments.
✓Cyanheads Obsidian MCP can read, list, search, create, append, patch, replace, delete, tag, and edit frontmatter in the configured vault through the Local REST API plugin.
The server defaults to full-vault access unless read paths, write paths, or read-only mode are configured.
Set `OBSIDIAN_READ_ONLY=true` for research-only workflows, then narrow writes with `OBSIDIAN_WRITE_PATHS` before allowing note edits.
Delete operations are permanent in the vault and should require human review even when the MCP host supports destructive-tool prompts.
Command-palette tools are disabled unless `OBSIDIAN_ENABLE_COMMANDS=true`; command execution can trigger opaque or destructive Obsidian plugin behavior.
Streamable HTTP deployments should use JWT or OAuth auth before being exposed beyond a trusted local machine.
✓Kordoc MCP Server reads local document files by absolute path and, by default, does not restrict access to a workspace directory.
The MCP source allowlists `.hwp`, `.hwpx`, `.pdf`, `.xlsx`, and `.docx` files, resolves symlinks, and applies a 500MB full-parse file limit.
Metadata-only parsing has a smaller 50MB limit, while archive, PDF, HWP5, and table parsers have additional resource limits documented in the security policy.
Form filling can write Markdown or HWPX files to an `output_path`; require confirmation before allowing an agent to create or overwrite documents.
Kordoc processes untrusted binary formats; keep the Node.js runtime and parser dependencies updated and avoid running it on high-privilege accounts.
The CLI also has watch and webhook flows; keep those separate from the MCP server unless you have reviewed outbound notification behavior.
Privacy notes
✓File paths, file contents, extracted text, OCR output, audio transcripts, webpage text, search results, prompts, tool arguments, and conversion errors may be visible to the MCP client and model provider.
Documents and media can contain personal data, customer material, credentials, internal plans, meeting recordings, legal drafts, and proprietary screenshots.
Avoid pointing the server at broad home, workspace, downloads, or cloud-sync directories unless every file in scope is approved for model access.
✓Workspaces, document titles, document bodies, comments, tags, database schemas, database rows, edgeless canvas data, notifications, user profiles, access-token metadata, blobs, and exported markdown can be sent to the MCP client and model.
API tokens, cookies, passwords, bearer tokens, OAuth config, and saved config files should be treated as secrets and kept out of prompts, logs, screenshots, issues, and committed MCP config.
Generated or modified documents can persist in AFFiNE and may become visible to collaborators depending on workspace permissions and sharing state.
Blob upload, cleanup, export, and publish/revoke workflows can expose files, generated content, or collaboration state beyond the current prompt.
✓Vault notes, headings, block references, frontmatter, tags, file metadata, outgoing links, search queries, command names, plugin status, and edit history may be exposed to the MCP client and model provider.
API keys, local plugin endpoints, HTTP auth settings, path allowlists, logs, OpenTelemetry traces, and Docker environment variables can reveal private vault structure or credentials.
Tag listing is vault-wide in upstream behavior and can reveal tag names outside narrowed read paths.
Notes may contain personal journals, client work, credentials, meeting notes, research plans, health data, or other sensitive knowledge-base content.
✓Parsed content can include full document text, tables, titles, authors, page counts, metadata, warnings, form labels, and filled values.
Document paths and resolved output paths can appear in MCP responses, CLI output, logs, or saved artifacts.
Government, legal, HR, finance, or customer documents may contain sensitive identifiers that become Markdown or JSON in the MCP client context.
HWPX form filling can preserve and rewrite original templates; store generated files only in approved directories.
Webhook or watch-mode workflows can send converted document information to third-party endpoints if enabled outside the MCP server.
Prerequisites
Node.js and npx available to the MCP client runtime.
Python and markitdown dependencies available for file conversion features.
Optional Docker setup if you want mounted read-only directories and explicit allowed paths.
MD_ALLOWED_PATHS configured when the server should be restricted to specific file directories.
Node.js and npm for installing the affine-mcp-server package.
AFFiNE Cloud API token or approved self-hosted AFFiNE credentials.
AFFiNE base URL for the Cloud or self-hosted deployment.
Clear workspace scope and least-privilege tool profile before enabling write, admin, destructive, blob, or access-token tools.
Node.js 24 or newer, or Bun 1.3.11 or newer.
Obsidian vault with the Obsidian Local REST API community plugin enabled.
Local REST API key stored in the MCP client environment.
Stdio MCP client, or reviewed Streamable HTTP deployment with authentication.
Node.js 18 or newer.
A local MCP client that can launch stdio servers with access to the documents you want parsed.
Optional `pdfjs-dist` support if you need PDF parsing in environments where the package is not already installed.
Approved directories for source documents and generated Markdown or HWPX output.