mcpField
M
markdown-notes-mcp

markdown-notes-mcp

Local
github.comProductivity0Updated 5w ago

About markdown-notes-mcp

markdown-notes-mcp is a local document-conversion server for MCP hosts such as Claude, VS Code, and Antigravity. It turns many file types into model-friendly Markdown without uploading documents, and can run image OCR on-device.

Key features

  1. 01Convert multiple document formats to Markdown
  2. 02Run image OCR on-device
  3. 03Convert files in a folder
  4. 04Save summaries beside documents
  5. 05Return short previews for long documents

Use cases

  1. 01Let an AI assistant read EPUBs or presentations
  2. 02Turn scanned images into readable text
  3. 03Convert document collections to Markdown

MCP support

It provides MCP tools to convert files and folders, save summaries, and list supported formats. It can be connected to hosts including Claude Desktop, VS Code, and Antigravity.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"narashiman-k-markdown-notes": {
"command": "npx",
"args": [
"-y",
"suprasuta-markdown-mcp"
],
"env": {
"MARKDOWN_MCP_ROOTS": "<MARKDOWN_MCP_ROOTS>",
"GEMINI_API_KEY": "<GEMINI_API_KEY>",
"ASSEMBLYAI_API_KEY": "<ASSEMBLYAI_API_KEY>"
}
}
}
}
Run commandnpx -y suprasuta-markdown-mcp
Environment variables to set
MARKDOWN_MCP_ROOTSSemicolon-separated folders the server may read. Omit to allow any path.
GEMINI_API_KEYSecretOptional. Enables cloud image recognition, which can also describe charts. Images are sent to Google only when cloud mode is chosen.
ASSEMBLYAI_API_KEYSecretOptional. Enables audio transcription, the only feature that cannot run locally.

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmsuprasuta-markdown-mcp0.1.4

Tools

4

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
pathstringYesAbsolute path to the file to convert.
savebooleanNoSet false to skip writing the .md file. Default true — the file is saved beside the original without needing to be asked for.
save_tostringNoAbsolute path to write the .md to, overriding the default of beside the original.
ocr_modeenumNoFor images only. "offline" (default) runs on this machine and uploads nothing. "cloud" sends the image to Google Gemini, which is more accurate and can describe charts, and requires GEMINI_API_KEY.offline | cloud
overwritebooleanNoSet true to replace an existing .md of the same name. Default false, in which case a numbered name is used instead so nothing is destroyed.
return_contentenumNo"auto" (default) returns the whole document if it is short, otherwise a preview and the saved path. "full" always returns everything — use only when the user genuinely needs the entire text in the conversation, as a long document can be tens of thousands of tokens. "none" saves and reports the path only, which is cheapest when the user just wants the file.auto | full | none

Details

From the project README

Suprasūtā Markdown Notes — MCP server

Let Claude, VS Code and Antigravity read any document on your machine — without uploading it.

Created by Narashiman Krishnamurthy


Licence: free for personal, non-commercial use. See LICENSE.md.

What it does

AI assistants can read plain text, and some can read PDFs. None of them read EPUB, OpenDocument, PowerPoint or a scanned image, and all of them do it by uploading your file to a server.

This converts documents on your own machine and hands back Markdown that has been tidied for a model to read — tables promoted to real Markdown tables, deep indentation flattened, code properly fenced.

DocumentsPDF, Word .docx, Excel .xlsx/.xls/.xlsm, PowerPoint .pptx, OpenDocument .odt/.ods, EPUB, CSV, TSV, plain text
ImagesOCR on the device, with no key and no network
AudioTranscription — the one feature that cannot run locally

Tools

ToolWhat it does
convert_to_markdownConverts one file and saves the .md beside the original automatically
convert_folder_to_markdownConverts several files into a chosen directory
save_summarySaves a summary the assistant wrote as <name>.summary.md beside the document
list_supported_formatsLists the extensions, and which optional cloud features are configured
About tokens

Converting costs you nothing — it all happens locally. But returning a long document into the conversation does cost tokens, at the same rate as pasting it in by hand.

So a long conversion is saved to disk and only a short preview comes back. A 50-page PDF costs roughly 400 tokens instead of 30,000. Short documents are returned in full, since they are cheap either way. Ask for return_content: "full" to override.

Installing

Claude Desktop — the easy way

Download the .mcpb file from Releases and double-click it. Claude Desktop installs it and asks which folders it may read, and optionally for API keys. No Node, no terminal, no JSON.

Claude Desktop — from source
npm install
npm run build
node scripts/install-claude-desktop.mjs --roots "D:\your\documents"

Then restart Claude Desktop completely. The script patches the existing config rather than replacing it, and writes a timestamped backup first.

--roots is optional but recommended: it limits which folders the server will read. Without it, any path the assistant asks for is allowed.

To remove it again: node scripts/install-claude-desktop.mjs --remove

From npm — any MCP host
npm install -g suprasuta-markdown-mcp

Then point your host at the suprasuta-markdown-mcp command, or run it without installing:

{
  "servers": {
    "suprasuta-markdown": {
      "command": "npx",
      "args": ["-y", "suprasuta-markdown-mcp"],
      "env": { "MARKDOWN_MCP_ROOTS": "D:\\your\\documents" }
    }
  }
}
VS Code and Antigravity

Both read a standard MCP configuration — the block above works as-is. Antigravity looks in ~/.gemini/config/mcp_config.json, or .agents/mcp_config.json inside a workspace.

To run a checkout rather than the published package, replace command and args with node and the absolute path to dist/server.js.

Optional cloud features

Both are dormant until a key is present. Everything else works without either.

VariableEnablesWhat leaves your machine
GEMINI_API_KEYCloud OCR, which can also describe charts and diagramsThe image, to Google
ASSEMBLYAI_API_KEYAudio transcriptionThe audio file, to AssemblyAI

Keys are read from the environment, never written to disk and never logged.

Settings are read once, at start-up. An MCP server is a long-running process, so a key or folder saved while it is running does not reach it until the host restarts. If a key you have just entered reports as not configured, restart the host before looking for anything more complicated.

Development

npm install          # .npmrc sets include=dev — do not delete it
npm run build        # stages the OCR engine, then bundles with esbuild
npm test             # 19 tests against the built bundle
npm run smoke        # converts every file in samples/ and reports
npm run typecheck
Why the build is esbuild rather than tsc

src/lib/convert/ is kept byte-identical to the copies in the Windows, web and Android apps, so that drift can be detected rather than discovered. Those files use extensionless imports and one Vite-specific ?url import, neither of which Node's own resolver accepts. esbuild resolves both, so the shared files never need Node-shaped edits.

The runtime hook

Three things genuinely differ between a browser and Node, and src/lib/convert/runtime.ts asks the host rather than sniffing for process:

HookWhy
tesseractPathsA browser needs URLs and its own worker; Node needs filesystem paths and must not be given the browser worker
docxSourcemammoth reads arrayBuffer in browsers and buffer under Node
ocrImageInputtesseract's Node build cannot decode a Blob; it wants a Buffer

Everything else is shared. src/runtime/node.ts supplies the Node answers and shims exactly one browser global, DOMParser.

A caution learned the hard way: that file used to define document too, and it broke OCR. tesseract.js sniffed for a DOM, found one, took the browser branch and died on window is not defined. Half a browser is worse than none — shim the minimum.

Keeping the copies honest
npm run sync:check              # list differences against all three apps
npm run sync:pull web           # bring the web app's version in
node scripts/sync-converters.mjs --push web

This package is the canonical copy: it is the only one with the runtime hook that lets identical files run in both environments, so fixes start here and flow outward. sync:check reports and exits zero — drift is information, not a build failure.

Privacy Policy

This software collects nothing. No account, no analytics, no telemetry, and no server of its own — document conversion happens entirely on your machine.

Two optional features send data to a third party, and only when you supply your own API key: cloud image recognition sends the image to Google, and audio transcription sends the audio to AssemblyAI. With no keys configured, the software makes no network connections at all. API keys are read from the environment, never written to disk and never logged.

Full policy, covering collection, storage, retention, third-party sharing and contact details: PRIVACY.md.

Related

Windows appMicrosoft Store · source
Web appmarkdown-notes-psi.vercel.app · source
AndroidInstall the web app from Chrome · older native build, no longer maintained

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.