About tooldash-mcp
tooldash-mcp is a local MCP server that gives AI agents PDF and text utilities without uploading files or making network calls. It suits people working with documents in MCP clients and includes safeguards against accidental file replacement.
Key features
- 01Inspect PDF pages and metadata
- 02Merge PDF files
- 03Extract selected PDF pages
- 04Clean and normalize text
- 05Restrict file access to a directory
Use cases
- 01Inspect a document's page count and metadata
- 02Combine reports and cover pages
- 03Create a PDF excerpt from selected pages
- 04Clean copied text before reuse
MCP support
Exposes PDF and text tools to MCP clients over a locally run server. Clients can launch it with npx or run it from a clone.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y tooldash-mcpTOOLDASH_MCP_ROOTOptional. Confines every file the server reads or writes to this directory.Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
4Saved tool list · updated 3w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| path | string | Yes | The PDF to inspect. Absolute, or relative to the client's working directory. |
Details
From the project READMEToolDash MCP
Offline PDF and text tools for AI agents. An MCP server that lets Claude Desktop, Cursor, VS Code and any other MCP client merge PDFs, pull out pages, inspect documents and clean up text — entirely on your own machine.
No upload. No API key. No account. No network call of any kind: the PDF work is done locally by pdf-lib, so a confidential contract never leaves your laptop.
Tools
| Tool | What it does | Writes files? |
|---|---|---|
pdf_info | Page count, per-page dimensions and metadata of a PDF | No |
merge_pdfs | Combine two or more PDFs into one, in the given order | Yes |
extract_pdf_pages | Copy a page selection ("1-3,7,10-12") into a new PDF | Yes |
clean_text | Collapse whitespace, strip invisible characters, normalize punctuation, optionally remove URLs | No |
The two tools that write files refuse to replace an existing file unless you pass overwrite: true, so an agent retrying a call cannot quietly destroy a document.
Requirements
Node.js 20 or newer.
Install
No install step — your MCP client runs it on demand with npx. Add the server to your client's config and restart it.
Claude Desktop
Edit claude_desktop_config.json:
- macOS —
~/Library/Application Support/Claude/claude_desktop_config.json - Windows —
%APPDATA%\Claude\claude_desktop_config.json - Linux —
~/.config/Claude/claude_desktop_config.json
{
"mcpServers": {
"tooldash": {
"command": "npx",
"args": ["-y", "tooldash-mcp"]
}
}
}
Restart Claude Desktop. The tools appear under the tools icon in the chat box.
Cursor
Create .cursor/mcp.json in your project (or ~/.cursor/mcp.json for every project):
{
"mcpServers": {
"tooldash": {
"command": "npx",
"args": ["-y", "tooldash-mcp"]
}
}
}
Then enable the server under Settings → MCP.
VS Code (GitHub Copilot agent mode)
Create .vscode/mcp.json:
{
"servers": {
"tooldash": {
"type": "stdio",
"command": "npx",
"args": ["-y", "tooldash-mcp"]
}
}
}
Running from a clone
git clone https://github.com/LassiB999/tooldash-mcp.git
cd tooldash-mcp
npm install
npm test
Then point your client at node /absolute/path/to/tooldash-mcp/server.js instead of npx.
Paths may be absolute, relative to the client's working directory, or start with ~. Surrounding quotes are stripped, so a path pasted as "/home/you/file.pdf" still works.
Restricting file access
The server reads and writes wherever your user account can. To confine it to one directory, set TOOLDASH_MCP_ROOT — any path outside it is refused with a clear error:
{
"mcpServers": {
"tooldash": {
"command": "npx",
"args": ["-y", "tooldash-mcp"],
"env": { "TOOLDASH_MCP_ROOT": "/home/you/Documents/pdfs" }
}
}
}
Usage examples
Ask your assistant in plain language — "merge these two PDFs and put the result on my desktop" — and it will fill in the calls below. The raw JSON is here for testing.
pdf_info
{ "path": "/home/you/Documents/report.pdf" }
report.pdf: 12 page(s), 248.3 KB. Title: "Q3 Report".
merge_pdfs
{
"inputPaths": ["/home/you/Documents/cover.pdf", "/home/you/Documents/report.pdf"],
"outputPath": "/home/you/Documents/final.pdf",
"overwrite": false
}
extract_pdf_pages
Pages are 1-based. Order is preserved, so "3,1-2" gives you page 3 first. A descending range like "5-1" reverses those pages.
{
"inputPath": "/home/you/Documents/report.pdf",
"pages": "1-3,7,10-12",
"outputPath": "/home/you/Documents/excerpt.pdf"
}
clean_text
{
"text": "Hello world \r\n\r\n\r\n\r\nSecond line ",
"collapseBlankLines": true,
"normalizeQuotes": false,
"removeUrls": false
}
removeUrls strips every http/https URL. The server is offline, so it cannot tell a working link from a dead one — it does not pretend to.
How it handles failure
Bad input comes back as a readable error result the model can act on, never as a crash: a missing file, a password-protected PDF, a page number past the end of the document, or an output path that already exists each produce a message saying what to do next. The server keeps running.
Diagnostics go to stderr only. stdout carries protocol frames and nothing else — the tests would fail if anything leaked into it.
Development
npm test # 15 end-to-end tests: a real MCP client over stdio, on real PDFs
npm run inspect # open the MCP Inspector against this server
Powered by ToolDash
ToolDash is a set of free, browser-based utilities — PDF, text, image, colour, developer and calculator tools — that run entirely in your tab with nothing uploaded. This server brings the same idea to your editor.
- tooldash.app — the full tool collection
- PDF Factory — the browser PDF studio these PDF tools mirror
- Al-Katib — Arabic keyboard and writing pad
License
MIT
Comments
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.