Data · Local MCP server

Diffgrab

Web page change tracking with structured diffs. markgrab + snapgrab integration.

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
io.github.ArkNill/diffgrab
Version
0.1.0
Status
Active
Category
data
Transport
stdio (local process)
Package
PyPI
Published
2026-03-18
Updated
2026-03-18
Publisher
ArkNill (GitHub) · 7 servers with pages here
Namespace
Namespace verified by the MCP Registry via GitHub (github.com/ArkNill) · how
Repository
github.com/QuartzUnit/diffgrab
Source
Registry API entry

Packages

RegistryPackageVersionTransportEnvironment variables
PyPIdiffgrab0.1.0stdioNone declared

How to connect Diffgrab

Diffgrab runs locally from a Python package published to PyPI: diffgrab version 0.1.0. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install - the usual command is uvx diffgrab.

In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):

{
  "mcpServers": {
    "diffgrab": {
      "command": "uvx",
      "args": [
        "diffgrab"
      ]
    }
  }
}

Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect

More from ArkNill (GitHub)

All 7 →
ServerRunsEndpoint or package
BrowsegrabToken-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab.Local · stdioPyPI: browsegrab
DocpickSchema-driven document extraction with local OCR + LLM. Document in, Structured JSON out.Local · stdioPyPI: docpick
EmbgrepLocal semantic search - embedding-powered grep for files, zero external services.Local · stdioPyPI: embgrep
FeedKitRSS/Atom feed collection with 417 curated feeds. Python MCP server.Local · stdioPyPI: feedkit
MarkGrabUniversal web content extraction - any URL to LLM-ready markdown. HTML, YouTube, PDF, DOCX.Local · stdioPyPI: markgrab
SnapgrabURL to screenshot with metadata. Python MCP server. Claude Vision optimized.Local · stdioPyPI: snapgrab

More data servers

All 4,815 →
ServerRunsEndpoint or package
DexioOne wiki for all your agents: pages read and written over MCP, a link graph, and broken-link checks.Remote · HTTPLive check: sign-in requiredapp.dexio.wiki
Diavgis - Greek Public ProcurementGreek public procurement: tenders, awards, contracts, payments, suppliers, expiring contracts.Remote · HTTPLive check: ✓ handshakemcp.diavgis.gr
DiffBeam Gaussian Beam OpticsRead-only optical catalog search plus DiffBeam server, schema, and catalog revision metadata.Remote · HTTPLive check: ✗ no handshakecatalog-api.gaussian-beam.com
DiffbotDiffbot MCP - Knowledge Graph company enrichment + web content extraction (diffbot.com)Remote · HTTPLive check: ✓ handshakegateway.pipeworx.io
DigiDataRead-only business data from Exact Online, Twinfield, AFAS and 30+ sources for your AI.Remote · HTTPLive check: sign-in requiredmcp.digi-data.nl
DigikalaUnofficial read-only Digikala: search products, compare sellers, price history, reviews, deals.Local · stdioPyPI: digikala-mcp
Digital Passport Assessment WorkbenchDeterministic SHACL-based assessment and comparison for digital passport data models.Local · stdioOCI image (Docker): ghcr.io/ce-rise-software/dpawb-mcp:0.1.2
DigitaltableteurDesign system contracts, docs search, and usage validation for @digitaltableteur components.Remote · HTTPLive check: ✓ handshakedigitaltableteur.com