Skip to main content
Glama
tooldash-mcp

tooldash-mcp

by LassiB999

ToolDash 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.

Powered by ToolDash


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.

Related MCP server: pdf-agent-toolkit-mcp

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.

License

MIT

Available Tools

4 tools
clean_textClean and normalize textA
Read-onlyIdempotent

Normalize messy text: collapse repeated spaces, strip trailing whitespace and invisible characters, unify line endings, and optionally collapse blank lines, convert smart punctuation to ASCII, or remove URLs. Runs entirely offline — nothing is uploaded and no network call is made.

Inputs: text (required), removeUrls, normalizeQuotes, collapseBlankLines. Returns: text, after, before, changed, +1 more

extract_pdf_pagesExtract PDF pagesA
Destructive

Write a selection of pages from a local PDF into a new file, leaving the original untouched. Pages are 1-based and may be given as a list and ranges, e.g. "1-3,7,10-12". Order is preserved, so "3,1" produces a two-page file in that order.

Inputs: pages (required), inputPath (required), outputPath (required), overwrite. Returns: pageCount, sizeBytes, outputPath, sourcePages

merge_pdfsMerge PDFsA
Destructive

Combine two or more local PDFs into a single file, in the order given. Runs entirely on this machine with pdf-lib — nothing is uploaded and no URL is fetched. Refuses to overwrite an existing output unless overwrite is true.

Inputs: inputPaths (required), outputPath (required), overwrite. Returns: sources, pageCount, sizeBytes, outputPath

pdf_infoInspect a PDFA
Read-onlyIdempotent

Report the page count, per-page dimensions and document metadata of a local PDF. Read-only: the file is never modified. Call this before merging or extracting so page numbers are known to be valid.

Inputs: path (required). Returns: name, path, pages, title, +3 more

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.2/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool targets a distinct action: reading PDF metadata, merging PDFs, extracting pages, and normalizing text. There is no overlap or boundary ambiguity, so an agent can select the right tool confidently.

    Naming Consistency4/5

    Three tools follow a clear verb_object pattern (merge_pdfs, extract_pdf_pages, clean_text), while pdf_info uses noun_noun rather than a verb-first form. This is a minor inconsistency in an otherwise predictable and readable naming scheme.

    Tool Count4/5

    Four tools is a reasonable size for a focused utility server, and none of the tools feel redundant. The mix of PDF operations with a standalone text cleaner makes the scope slightly broad, but the count itself is not too thin or bloated.

    Completeness4/5

    The PDF workflow covers the key needs of inspection, merging, and page extraction, while clean_text works as a self-contained text utility. Missing operations like PDF text extraction, rotation, or encryption are plausible additions, but agents can complete core merge, extract, and cleanup tasks without dead ends.

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to perform comprehensive PDF operations locally, including compression, text extraction, PII redaction, page organization, splitting, merging, watermarking, creation, and form filling, all without cloud uploads.
      22 npm
      -
    • A
      license
      B
      quality
      B
      maintenance
      Enables AI agents to perform local-first PDF processing entirely on-device, including OCR write-back to make scans searchable, unlocking and re-encrypting PDFs, splitting/merging/rotating pages, and compressing files, with no cloud calls or file uploads.
      25
      1
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables AI agents to inspect and work with PDF files entirely on the local machine, covering page counts, metadata, layout, encryption permissions, scan-vs-text detection, and page rendering. Generated results land in a temporary workspace as short artifact ids that can be chained between tools and exported to real folders on request.
      12
      56 PyPI
      1
      Apache 2.0