DiffMint by Harlo is answering right now. Last checked 8 min ago. It exposes 3 tools.
Diff two texts by line, word or char: unified diff, HTML redline, patch apply, similarity.
Today is the operative word: we check DiffMint by Harlo every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 8 min ago.
claude mcp add diffmint --transport http https://diffmint.mike-tusa.workers.dev/mcp
https://diffmint.mike-tusa.workers.dev/mcp
[mcp_servers.diffmint]
url = "https://diffmint.mike-tusa.workers.dev/mcp"
{
"mcpServers": {
"diffmint": {
"url": "https://diffmint.mike-tusa.workers.dev/mcp"
}
}
}
{
"servers": {
"diffmint": {
"type": "http",
"url": "https://diffmint.mike-tusa.workers.dev/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
apply_patch
diff_text
text_similarity
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://diffmint.mike-tusa.workers.dev/mcp | streamable-http | answering | 55 ms | 8 min ago |
Unified diffs of two texts: change hunks with context, plus added and removed line counts
Character-precise unified diff + patch application + patch parsing.
Create, check and apply unified diffs offline, with no shell and no repository needed
Read, convert, search, diff and outline PDF, Word, PowerPoint, HTML and 40+ formats as Markdown.
Find free-to-use stock photos by words, by image or by similarity; every result names its licence.
Visual search for memes, infographics and charts — by meaning, OCR text, or image similarity.
Store and retrieve text in a Qdrant vector database by similarity search.
Compare two texts or files and show line changes locally. No network and no key.
Answers built from our own checks of this server.