Skip to main content
Glama

SRT Lint MCP

An MCP server that lints and safely fixes SubRip (.srt) subtitle files. It reuses the same engine as the SRT Subtitle Lint VS Code extension and the free in-browser SRT Subtitle Checker.

This is a free side project by Stanley J. MIT licensed. It is not published to npm yet (an npm account is still needed for that).

Tools

Tool

What it does

lint_srt

Diagnostics for cue numbering, invalid or odd timestamps, end-before-start, zero duration, overlaps, reading speed (CPS), line length, empty cues, too many lines, and WebVTT labelled as SRT

fix_srt

Safe fixes only: renumber cues, normalize timestamps to HH:MM:SS,mmm, wrap long lines. Does not change overlaps, negative/zero duration, or high CPS

srt_stats

Cue count, total duration, span, average/max CPS, and a per-cue breakdown

Character counts use Intl.Segmenter graphemes and ignore simple subtitle markup ({\an8}, <i>…</i>). Defaults: 42 / 16 characters per line (Latin / CJK) and 21 / 9 CPS.

Pass the file contents in the srt argument (not a path — the server does not read the client’s disk).

Related MCP server: aegisub-mcp

Run

Requires Node.js 18+. From a clone:

npm install
npm test
npm start

npm start (or npx srt-lint-mcp once the package is installed) speaks MCP on stdio. Do not type into that process yourself; a client such as Claude Desktop or Cursor launches it.

Until the package is on npm, you can point a client at a clone, or run from GitHub:

npx -y github:todanley/srt-lint-mcp

(npx will run prepare / tsc on first install from GitHub.)

Claude Desktop

Add this to the Claude Desktop config (claude_desktop_config.json on macOS: ~/Library/Application Support/Claude/; on Windows: %APPDATA%\Claude\).

From a local clone:

{
  "mcpServers": {
    "srt-lint": {
      "command": "node",
      "args": ["/ABS/PATH/TO/srt-lint-mcp/dist/index.js"]
    }
  }
}

Or, after a GitHub install:

{
  "mcpServers": {
    "srt-lint": {
      "command": "npx",
      "args": ["-y", "github:todanley/srt-lint-mcp"]
    }
  }
}

Restart Claude Desktop after saving.

Cursor

In Cursor, add an MCP server in Settings → MCP, or put this in .cursor/mcp.json (project) or ~/.cursor/mcp.json (user):

{
  "mcpServers": {
    "srt-lint": {
      "command": "node",
      "args": ["/ABS/PATH/TO/srt-lint-mcp/dist/index.js"]
    }
  }
}

The npx -y github:todanley/srt-lint-mcp form works here too. Reload MCP (or restart Cursor) after saving.

Docker (stdio)

docker build -t srt-lint-mcp .
docker run --rm -i srt-lint-mcp

glama.json names todanley as the maintainer. Smithery config is in smithery.yaml. The server has not been submitted to mcp.so, Glama, or Smithery, and it is not on npm.

Available Tools

3 tools
fix_srtApply safe SRT fixesA

Apply only safe, mechanical fixes to an SRT document: renumber cues to 1…n (inserting a missing index), normalize timestamps to HH:MM:SS,mmm, and wrap long lines at spaces (English) or at a character (CJK). Does not change overlaps, negative/zero duration, or high CPS — those need a human look. Returns the updated SRT text and remaining issue counts.

Inputs: srt (required), fixes, maxCpsEn, maxCpsCjk, +2 more.

lint_srtLint an SRT fileA

Parse a SubRip (.srt) document and return diagnostics for cue numbering, invalid or odd timestamps, end-before-start (negative duration), zero duration, overlaps, reading speed (CPS), line length, empty cues, too many lines, and WebVTT mislabelled as SRT. Character counts use Intl.Segmenter graphemes and ignore simple subtitle markup.

Inputs: srt (required), maxCpsEn, maxCpsCjk, maxCharsEn, +1 more.

srt_statsSRT timing and CPS statsB

Summarise an SRT document: cue count, total on-screen duration, span from first start to last end, average and max characters-per-second, and a per-cue breakdown of start/end, duration, character count, and CPS. Uses the same grapheme rules as lint_srt.

Inputs: srt (required), maxCpsEn, maxCpsCjk, maxCharsEn, +1 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.8/5.0

    Scored across 3 tools

    Disambiguation4/5

    Each tool has a distinct role: lint_srt returns diagnostics, fix_srt applies mechanical repairs, and srt_stats returns a quantitative summary. There is partial overlap since CPS, character counts, and line length surface in both lint_srt and srt_stats, but the output framing (problems vs. metrics) keeps them separable.

    Naming Consistency4/5

    lint_srt and fix_srt follow a clean verb_noun pattern, while srt_stats breaks it with a noun-first form. The deviation is minor and the subject (srt) is consistent across all three, so the set remains predictable.

    Tool Count4/5

    Three tools is lean but each maps to a genuine operation (diagnose, repair, summarise) for a narrow SRT-focused domain. There is little dead weight, though the surface is close to the thin end.

    Completeness4/5

    The diagnose/fix/measure lifecycle covers the core SRT workflow, and fix_srt deliberately scopes to safe fixes. Gaps are minor: no selective or per-issue-type fixing, no format conversion (e.g. WebVTT output), and no re-validation pass bundled with fixes.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      C
      maintenance
      Enables MCP clients to open, read, edit, verify, and save Aegisub/ASS subtitle documents, covering event lines, styles, timing and QC, karaoke, override tags, vector drawings, clipping, and font metrics. Includes a libass-backed verification layer and byte-faithful round-trips, served over stdio or streamable HTTP.
      121
      1
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables MCP clients such as Claude, Cursor and VS Code to validate SRT and WebVTT caption files mid-task against Netflix, BBC or DCMP limits, flagging reading speed, line length, line count, on-screen duration, gaps, overlaps and broken timestamps. Runs locally as a dependency-free stdio server, accepting a file path or pasted caption text and exposing each standard's limits with their source pages.
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables an AI agent to inspect, repair, retime, convert, merge/split, and search SRT, WebVTT, and ASS subtitle files entirely offline, with exact-fraction resync, dry-run fixes, and honest encoding detection. Translation is handled by the agent itself through a chunk/apply contract that preserves timing and flags lost tags.
      10
      MIT