# Hex Line (npm · @levnikolaevich/hex-line-mcp)

Hash-verified file editing MCP server with token efficiency hook for AI coding agents.

- Trust score: 72/100 (medium)
- Change this week: −10
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-04

## Components

- npm · `@levnikolaevich/hex-line-mcp`: 72/100 (this document), [markdown](https://verifymcp.io/servers/levnikolaevich-hex-line-mcp/levnikolaevich-hex-line-mcp.md), [page](https://verifymcp.io/servers/levnikolaevich-hex-line-mcp/levnikolaevich-hex-line-mcp)

## Channel facts

- Registry: `npm`
- Package: `@levnikolaevich/hex-line-mcp`
- Version: `1.31.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-04.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (145 of 149), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (145 of 149), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to levnikolaevich/claude-code-skills).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 67 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 36/100
  - AI-judged instruction clarity (fair).
  - Context-footprint check failed: tool/resource definitions use about 1759 tokens (~195/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add levnikolaevich-hex-line-mcp -- npx -y @levnikolaevich/hex-line-mcp
```

### Codex

```bash
codex mcp add levnikolaevich-hex-line-mcp -- npx -y @levnikolaevich/hex-line-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "levnikolaevich-hex-line-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@levnikolaevich/hex-line-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add levnikolaevich-hex-line-mcp --command npx --arg -y --arg @levnikolaevich/hex-line-mcp
```

### Hermes

```yaml
mcp_servers:
  levnikolaevich-hex-line-mcp:
    command: "npx"
    args: ["-y", "@levnikolaevich/hex-line-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "levnikolaevich-hex-line-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@levnikolaevich/hex-line-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-04 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-03 (score 71, +26)

- [security improvement] Known CVEs: unverified → partial
- [security improvement] Provenance: unverified → pass
- [security improvement] Install scripts: unverified → pass
- [security] The attested source repository moved: levnikolaevich/claude-code-skills
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] License: unverified → pass
- [functional] Licence: MIT

### 2026-08-02 (score 45, +18)

- [security improvement] Malware scan: unverified → pass
- [functional improvement] Stability: unverified → 0.20

### 2026-08-01 (score 27, +22)

- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Tool coverage: unverified → 100

### 2026-07-31 (score 5, −25)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 30, −52)

- [security regression] Provenance: pass → unverified
- [security regression] Known CVEs: partial → unverified
- [security regression] Malware scan: pass → unverified
- [security regression] Install scripts: pass → unverified
- [security] The attested source repository moved: levnikolaevich/claude-code-skills
- [functional regression] Dependency health: partial → unverified
- [functional regression] License: pass → unverified
- [functional regression] Maintenance: pass → unverified
- [functional] Licence: MIT

### 2026-07-27 (score 82, +57)

- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Provenance: unverified → pass
- [security] The attested source repository moved: levnikolaevich/claude-code-skills
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] License: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Tool coverage: 100
- [functional] First check of Tool coverage: 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: fair
- [functional] First check of Schema quality: fail
- [functional] Licence: MIT

### 2026-07-26 (score 25)

First indexed and scored.

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

## MCP tools (9)

### `read_file` (~200 tokens)

Read File

Read file with progressive disclosure. Default: minimal plain partial read for discovery; enable edit-ready metadata explicitly when preparing a verified edit.

Input parameters:

- `edit_ready` (boolean): Include hash/checksum edit protocol blocks explicitly. Default: false for discovery reads.
- `file_path` (string): File path
- `file_paths` (array): Array of file paths to read (batch mode)
- `limit` (number): Max lines (default: 200 for discovery, 2000 for edit-ready, 0 = all)
- `offset` (number): Start line (1-indexed, default: 1)
- `plain` (boolean): Omit hashes (lineNum|content)
- `ranges`: Line ranges, e.g. ["10-25", {"start":40,"end":55}]
- `verbosity` (string): Response budget. `minimal` is discovery-first, `compact` adds revision context, `full` preserves the richest payload.

Output parameters:

- `code` (string)
- `content` (string)
- `edit_ready` (boolean)
- `error` (object)
- `failure_class` (string)
- `file_path` (string)
- `file_paths` (array)
- `next_action` (string)
- `recovery` (string)
- `status` (string)
- `summary` (string)

### `edit_file` (~479 tokens)

Edit File

Apply hash-verified partial edits to one file. Batch ALL hunks for the same file into ONE call via the `edits` array -- separate sequential edit_file calls on one file go stale and conflict (the most common edit failure). Carry base_revision only for a genuinely later follow-up after the file changed. Anchors accept tag.N, a bare line number, or unique line content (auto-resolved); range_checksum accepts "auto" to compute it for the current range. Preserves existing line endings and trailing-newline shape; conservative conflicts return retry helpers. boundary_mode=inclusive deletes the anchor lines themselves; new_text must close any delimiter whose opening falls inside the replaced range.

Input parameters:

- `allow_external` (boolean): Allow editing a path outside the current project root. Use only when you intentionally target a temp or external file.
- `base_revision` (string): Prior revision from read_file/edit_file. Enables conservative auto-rebase for same-file follow-up edits.
- `conflict_policy` (string): Conflict handling (default: "conservative"). "conservative" returns structured CONFLICT output with recovery_ranges, retry_edit/retry_edits, suggested_read_call, and retry_plan when available.
- `dry_run` (boolean): Preview changes without writing
- `edits` (required): JSON array of canonical edits. [{"set_line":{"anchor":"ab.12","new_text":"x"}}] [{"replace_lines":{"start_anchor":"ab.10","end_anchor":"cd.15","new_text":"x","range_checksum":"10-15:a1b2"}}] [{"inser…
- `file_path` (string, required): File to edit
- `restore_indent` (boolean): Auto-fix indentation to match anchor (default: false)

Output parameters:

- `code` (string)
- `content` (string)
- `error` (object)
- `failure_class` (string)
- `file_path` (string)
- `next_action` (string)
- `reason` (string)
- `recovery` (string)
- `status` (string)
- `summary` (string)
- `warnings` (array)

### `write_file` (~81 tokens)

Write File

Create a new file or overwrite existing. Creates parent dirs. For existing files prefer edit_file (shows diff, verifies hashes).

Input parameters:

- `allow_external` (boolean): Allow writing a path outside the current project root. Use only when you intentionally target a temp or external file.
- `content` (string, required): File content
- `file_path` (string, required): File path

Output parameters:

- `code` (string)
- `error` (object)
- `failure_class` (string)
- `file_path` (string)
- `lines` (number)
- `next_action` (string)
- `recovery` (string)
- `status` (string)
- `summary` (string)

### `grep_search` (~364 tokens)

Search Files

Search file contents with ripgrep. Default: summary-first discovery output; use `content` with `edit_ready=true` when you need verified edit hunks.

Input parameters:

- `allow_large_output` (boolean): Bypass the default content-mode block/char caps when you intentionally need a larger payload.
- `case_insensitive` (boolean): Ignore case (-i)
- `context` (number): Symmetric context lines around matches (-C)
- `context_after` (number): Context lines AFTER match (-A)
- `context_before` (number): Context lines BEFORE match (-B)
- `edit_ready` (boolean): Preserve hash/checksum search hunks in `content` mode. Default: false.
- `glob` (string): Glob filter (e.g. "*.ts")
- `head_limit` (number): Total match events across all files; multiline matches count as 1 (default: 50 for summary discovery, 200 for content, 1000 for files_with_matches/count, 0 = unlimited)
- `limit` (number): Max matches per file (default: 20 for summary discovery, 100 for content)
- `literal` (boolean): Literal string search, no regex (-F)
- `multiline` (boolean): Pattern can span multiple lines (-U)
- `output_mode` (string): Output format (default: summary)
- `path` (string): Search dir/file (default: cwd)
- `pattern` (string, required): Search pattern (regex by default, literal if literal:true)
- `plain` (boolean): Omit hash tags, return file:line:content
- `smart_case` (boolean): CI when pattern is all lowercase, CS if uppercase (-S)
- `type` (string): File type (e.g. "js", "py")

Output parameters:

- `code` (string)
- `content` (string)
- `error` (object)
- `failure_class` (string)
- `next_action` (string)
- `pattern` (string)
- `recovery` (string)
- `status` (string)
- `summary` (string)

### `outline` (~58 tokens)

File Outline

AST-based structural outline with hash anchors for direct edit_file usage. Supports JavaScript/TypeScript, Python, C#, and PHP code files plus markdown headings (.md/.mdx, fence-aware).

Input parameters:

- `file_path` (string, required): Source file path

Output parameters:

- `code` (string)
- `content` (string)
- `error` (object)
- `failure_class` (string)
- `file_path` (string)
- `next_action` (string)
- `reason` (string)
- `recovery` (string)
- `status` (string)
- `summary` (string)

### `verify` (~103 tokens)

Verify Checksums

Check if held checksums are still valid without rereading. Use before delayed or mixed-tool follow-up edits; returns canonical status, next_action, and reread guidance.

Input parameters:

- `base_revision` (string): Optional prior revision to compare against latest state.
- `checksums` (array, required): Checksum strings, e.g. ["1-50:f7e2a1b0", "51-100:abcd1234"]
- `file_path` (string, required): File path

Output parameters:

- `code` (string)
- `content` (string)
- `error` (object)
- `failure_class` (string)
- `file_path` (string)
- `next_action` (string)
- `reason` (string)
- `recovery` (string)
- `status` (string)
- `summary` (string)

### `inspect_path` (~223 tokens)

Inspect Path

Inspect a file or directory path. Files return compact metadata; directories return a gitignore-aware tree or pattern matches.

Input parameters:

- `format` (string): "compact" = shorter path view, "full" = include sizes/metadata where available
- `gitignore` (boolean): Respect root .gitignore patterns (default: true). Nested .gitignore not supported
- `max_depth` (number): Max recursion depth (default: 2 for discovery, or 20 in pattern mode)
- `max_entries` (number): Max entries to show in pattern mode before truncation metadata is returned (default: 60, 0 = unlimited)
- `path` (string, required): File or directory path
- `pattern` (string): Glob filter on names (e.g. "*-mcp", "*.mjs"). Returns flat match list instead of tree
- `type` (string): "file", "dir", or "all" (default). Like find -type f/d
- `verbosity` (string): Response budget. `minimal` returns the shortest tree summary.

Output parameters:

- `code` (string)
- `content` (string)
- `error` (object)
- `failure_class` (string)
- `next_action` (string)
- `path` (string)
- `reason` (string)
- `recovery` (string)
- `status` (string)
- `summary` (string)

### `changes` (~67 tokens)

Semantic Diff

Semantic diff against git ref (default: HEAD). Returns canonical status, summary, next_action, changed symbols, and graph-backed risk hints when available.

Input parameters:

- `compare_against` (string): Git ref to compare against (default: "HEAD")
- `path` (string, required): File or directory path

Output parameters:

- `code` (string)
- `content` (string)
- `error` (object)
- `failure_class` (string)
- `next_action` (string)
- `path` (string)
- `recovery` (string)
- `status` (string)
- `summary` (string)

### `bulk_replace` (~184 tokens)

Bulk Replace

Search-and-replace text across multiple files inside an explicit root path. Use for renames and refactors when the project scope is known.

Input parameters:

- `allow_external` (boolean): Allow a replacement root outside the current project root. Use only when you intentionally target a temp or external directory.
- `dry_run` (boolean): Preview without writing (default: false)
- `format` (string): "compact" (default) = summary only, "full" = include capped diffs
- `glob` (string): File glob (default: "**/*.{md,mjs,json,yml,ts,js}")
- `max_files` (number): Max files to process (default: 100)
- `path` (string, required): Root directory for the replacement scope
- `replacements` (required): JSON array of {old, new} pairs: [{"old":"foo","new":"bar"}]

Output parameters:

- `code` (string)
- `content` (string)
- `error` (object)
- `failure_class` (string)
- `next_action` (string)
- `path` (string)
- `reason` (string)
- `recovery` (string)
- `status` (string)
- `summary` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/levnikolaevich-hex-line-mcp/levnikolaevich-hex-line-mcp#diagnostics

## Score history

- 2026-08-04: 72
- 2026-08-03: 71
- 2026-08-02: 45
- 2026-08-01: 27
- 2026-07-31: 5
- 2026-07-30: 30
- 2026-07-28: 82
- 2026-07-27: 82
- 2026-07-26: 25

## Links

- npm package: https://www.npmjs.com/package/@levnikolaevich/hex-line-mcp
- Socket report: https://socket.dev/npm/package/@levnikolaevich/hex-line-mcp
- Repository: https://github.com/levnikolaevich/claude-code-skills
- Changelog RSS feed: https://verifymcp.io/servers/levnikolaevich-hex-line-mcp/levnikolaevich-hex-line-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/levnikolaevich-hex-line-mcp/levnikolaevich-hex-line-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/levnikolaevich-hex-line-mcp/levnikolaevich-hex-line-mcp