Pdf Edit Mcp

media MCP Server

MCP server for format-preserving PDF text editing — find, replace, and batch-edit text in existing PDFs while preserving fonts, layout, and visual fidelity. Powered by pdf-edit-engine.

VerifiedInstall Ready
mediamedia
2 views1 stars0 forksMIT

Why This Matters

Discovered via github-topic:mcp-server and last synced 3mo ago.

VerifiedInstall Ready
Source
github-topic:mcp-server
Stars
1
Last synced
3mo ago
Install
Instructions detected

Install

1. Install the package

uvx pdf-edit-mcp

2. Add to claude_desktop_config.json

{
  "mcpServers": {
    "pdf-edit-mcp": {
      "command": "npx",
      "args": [
        "pdf-edit-mcp"
      ]
    }
  }
}

Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) / %APPDATA%\Claude\claude_desktop_config.json (Windows)

41
Tools
0
Resources
0
Prompts
Standard I/O
Transport

Available Tools (41)

pdf_inspect

Complete document overview — text, fonts, paragraphs, annotations in one call. Start here before editing.

pdf_replace_text

Replace all occurrences of a string (names, dates, typos, labels)

pdf_replace_section

Replace a section's entire content by fuzzy title match

pdf_add_bookmark

Add a navigation bookmark pointing to a page

Re-calculated

Exact original coordinates

pdf_detect_paragraphs

Detect paragraph boundaries with bounding boxes on a page

pdf_detect_sections

Analyze document structure — section tree with titles, bounding boxes, and text

pdf_insert_text_block

Insert text at a position

pdf_delete_block

Delete content in a bounding box, optionally close the gap

pdf_move_annotation

Move an annotation to a new position

pdf_add_hyperlink

Add a clickable hyperlink to a page region

pdf_crop_pages

Crop all pages to a bounding box

pdf_add_watermark

Overlay a watermark PDF on all pages

None

FidelityReport on every edit (`font_preserved`, `font_substituted`, `glyphs_missing`, `overflow_detected`, typed `degradations`)

Tool

Description

pdf_get_text

Extract all text from a PDF

pdf_find_text

Find all occurrences of a string with page numbers and bounding box positions

pdf_get_fonts

List fonts with encoding type, glyph count, PostScript name, subset status

pdf_get_text_layout

Get every text block with exact position, font, and size

pdf_extract_bbox_text

Extract text from a bounding box region with gap-aware joining

pdf_analyze_subset

Check if an embedded font can render specific characters before editing

pdf_replace_single

Replace one specific occurrence by match index

pdf_batch_replace

Multiple find-and-replace edits in one atomic operation (up to 500 edits)

pdf_replace_block

Replace all content within a bounding box with new text (`fit="shrink"` to shrink-to-fit)

pdf_batch_replace_block

Replace content in multiple bounding boxes atomically

pdf_swap_sections

Swap two sections by fuzzy title match — re-renders all siblings for uniform spacing

pdf_get_annotations

List all annotations with positions, types, and URLs

pdf_add_annotation

Add a link annotation at a position on a page

pdf_update_annotation

Update a link annotation's target URL

pdf_delete_annotation_v2

Delete an annotation by page and index

pdf_add_highlight

Add a highlight annotation with QuadPoints

pdf_flatten_annotations

Flatten all annotations into page content (non-editable)

pdf_merge

Merge multiple PDFs into one document

pdf_split

Split a PDF into individual page files

pdf_reorder_pages

Reorder pages by 0-indexed page number array

pdf_rotate_pages

Rotate pages by 90, 180, or 270 degrees

pdf_delete_pages

Delete specific pages (0-indexed)

pdf_edit_metadata

Edit title, author, subject, creator, producer

pdf_encrypt

Encrypt with owner and user passwords

pdf_decrypt

Decrypt a password-protected PDF

pdf_fill_form

Fill form fields by name-value pairs