Integration

Diffchecker integration

Diffchecker compares two versions of the same content and reports what changed: two texts (added and removed chunks, row by row), two PDFs (plain-text or rich-text diff with styles and positions), two images (changed pixels and a diff picture), two spreadsheets (cell, row and column changes) and two Word files (a redline DOCX with tracked changes). Every diff consumes credits from the plan's monthly quota according to the size of the larger input; test_auth is free. The legacy pdf routes, the HTML output formats and the base64 data-URL upload variant are not exposed (files are sent as uploads). Authentication: paid plans send an API key in the X-Api-Key header; the free tier (50 diffs a month) sends any email address as the email query parameter instead.

Connect Diffchecker How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Diffchecker.Built from the 7 Diffchecker tools below, on the connection you add once.

What you can do with Diffchecker

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Auth test, 1 operation

test_authTest authGETChecks that the connected credential (API key or free-tier email) is accepted, without consuming any credit. Returns a confirmation message and creditsUsed (always 0).

Excel, 1 operation

compare_spreadsheetsCompare spreadsheetsPOSTCompares two spreadsheets (.xlsx, .xls or .csv) and returns the cell-by-cell diff table, row and column change metadata and summary stats. Columns are paired by header and content, so renamed columns still match. Consumes credits: 1 per 15,000 cells.

Image, 1 operation

compare_imagesCompare imagesPOSTCompares two images and returns the diff picture as a PNG data URL, the number and percentage of differing pixels, and the dimensions of both inputs. Consumes credits: 1 per 4,000,000 pixels of the larger image.

Plaintext, 1 operation

compare_pdf_plain_textCompare pdf plain textPOSTCompares the extracted text of two PDF files and returns rows of changes plus added and removed chunk counts. Consumes credits: 1 per 3 pages of the larger PDF.

Redline, 1 operation

compare_docx_redlineCompare docx redlinePOSTCompares two Word documents and returns a DOCX file (the revised document with every difference shown as Microsoft Word tracked changes). Consumes credits: 1 per 100,000 bytes of the larger DOCX.

Richtext, 1 operation

compare_pdf_rich_textCompare pdf rich textPOSTCompares two PDF files as rich text: text changes with their page polygons, optional style changes (font family, size, color) and visual object changes, plus page sizes of both documents. Consumes credits: 1 per page of the larger PDF.

Text, 1 operation

compare_textCompare textPOSTCompares two texts and returns the diff as rows (each with the left and right side of the line and its changed chunks) plus the count of added and removed chunks. Consumes credits: 1 per 300,000 characters of the larger text.

Use Diffchecker from Claude Code, Cursor or Codex

Connect Diffchecker in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Diffchecker operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Diffchecker

Create your workspace
Sign up free. Nothing to install.
Connect Diffchecker once
Add your Diffchecker connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.