DiffMint by Harlo
Server Details
Diff two texts by line, word or char: unified diff, HTML redline, patch apply, similarity.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 3 tools
The three tools map to clearly different operations: applying a patch, producing a diff, and computing a similarity ratio. The only mild overlap is that diff_text already returns similarity stats, making text_similarity partially redundant, but the dedicated single-metric tool is still easy to distinguish.
All names use snake_case, and two of three follow a verb_noun action pattern (apply_patch, diff_text). text_similarity is a noun phrase describing an output rather than an action, a minor but noticeable deviation from the otherwise predictable convention.
Three tools is a lean, well-scoped surface for a deterministic text-diff utility, and each tool earns its place. It sits at the thin end of the appropriate range, with no filler tools but little room for convenience helpers.
The core lifecycle of diffing, patching, and similarity scoring is covered, with limits and failure modes documented. Known gaps are explicitly acknowledged (no 3-way merge, single-file patches only, no binary files), which agents can work around but which leave the surface slightly incomplete.
Available Tools
3 toolsapply_patchApply a unified diffARead-onlyIdempotentInspect
Apply a single-file unified diff (patch) to text and return the patched text, or applied:false if a hunk does not match. Optional fuzz 0-2.
Inputs: text (required), patch (required), fuzz.
diff_textDiff two textsARead-onlyIdempotentInspect
Compare text a with text b by lines (default), words or chars. Returns ops (equal/insert/delete), a unified diff (lines mode), optional escaped HTML redline, stats and similarity. Deterministic diff (Myers algorithm via jsdiff), not an AI or semantic comparison. Limits per side: lines mode 64 KB and 1,000 lines, words mode 8 KB, chars mode 4 KB. If the texts need more than 250 inserted plus deleted units, the API returns 422 too_different instead of a partial diff. Patches up to 64 KB apply to text up to 64 KB. No 3-way merge, no binary files. Stateless: text is not stored or logged; no URL fetching.
Inputs: a (required), b (required), mode, context, +5 more.
text_similarityText similarity scoreARead-onlyIdempotentInspect
Similarity ratio 0-1 between two texts (2 x unchanged chars / total chars) on chars (default), words or lines granularity, plus change stats.
Inputs: a (required), b (required), mode, ignore_case.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Exact text tools for AI agents: unified diff, patch apply, regex testing, grapheme counting.
Diff two npm/PyPI versions or lockfiles: new install scripts, network/shell/eval calls, new deps.
Analyse and clean up text: stats, language, keywords, summary, sentiment, PII redaction, diff.
Returns what was added, removed or changed between two Apify datasets, files, Google Sheets or...
Related MCP Servers
- AlicenseAqualityDmaintenanceProvides exact text analysis tools for counting characters and words, scoring readability, diffing texts, testing regular expressions, and computing hashes.5MIT
- AlicenseNot gradedqualityDmaintenanceTransforms code diffs into beautiful visual comparisons with support for GitHub Gist sharing and local file output (HTML/PNG).12 npm12MIT
- AlicenseBqualityDmaintenanceThis server provides a tool to generate unified diffs between two text strings, facilitating text comparison and analysis.116 npm3MIT

mcp-diffofficial
AlicenseNot gradedqualityCmaintenanceComputes line-level diffs between two texts, returning added/removed lines and a unified diff string.82 npmMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.