# Repomix (npm · repomix)

Pack local or remote codebases into AI-friendly files that LLMs and coding agents can read or search

- Trust score: 81/100 (high trust)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-24

## Components

- npm · `repomix`: 81/100 (this document), [markdown](https://verifymcp.io/servers/yamadashy-repomix/repomix.md), [page](https://verifymcp.io/servers/yamadashy-repomix/repomix)

## Channel facts

- Registry: `npm`
- Package: `repomix`
- Version: `1.18.1`
- 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 2026-09-24.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 57 of 171 dependencies flagged as unhealthy (1 deprecated).
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to yamadashy/repomix).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 3 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 76/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2026 tokens (~337/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **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.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the Repomix MCP server?

Repomix runs locally as an npm package, launched with npx -y repomix. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add yamadashy-repomix -- npx -y repomix
```

### Cursor

```json
{
  "mcpServers": {
    "yamadashy-repomix": {
      "command": "npx",
      "args": [
        "-y",
        "repomix"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "yamadashy-repomix": {
      "command": "npx",
      "args": [
        "-y",
        "repomix"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add yamadashy-repomix -- npx -y repomix
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add yamadashy-repomix --command npx --arg -y --arg repomix
```

### Hermes

```yaml
mcp_servers:
  yamadashy-repomix:
    command: "npx"
    args: ["-y", "repomix"]
```

### Netclaw

```json
{
  "McpServers": {
    "yamadashy-repomix": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "repomix"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add yamadashy-repomix -t stdio -c npx -a -y repomix
```

### Other

```json
{
  "mcpServers": {
    "yamadashy-repomix": {
      "command": "npx",
      "args": [
        "-y",
        "repomix"
      ]
    }
  }
}
```

## 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.

### 2026-09-21 (score 81)

First indexed and scored.

## MCP tools (6)

### `pack_codebase` (~493 tokens)

Pack Local Codebase

Package a local code directory into a consolidated file for AI analysis. This tool analyzes the codebase structure, extracts relevant code content, and generates a comprehensive report including metrics, file tree, and formatted code content. Supports multiple output formats: XML (structured with <file> tags), Markdown (human-readable with ## headers and code blocks), JSON (machine-readable with files as key-value pairs), and Plain text (simple format with separators). Also supports Tree-sitter compression for efficient token usage.

Input parameters:

- `compress` (boolean): Enable Tree-sitter compression to extract essential code signatures and structure while removing implementation details. Reduces token usage by ~70% while preserving semantic meaning. Generally not n…
- `directory` (string, required): Directory to pack (Absolute path). Any directory readable by this process can be packed.
- `ignorePatterns` (string): Specify additional files to exclude using fast-glob patterns. Multiple patterns can be comma-separated (e.g., "test/**,*.spec.js", "node_modules/**,dist/**"). These patterns supplement .gitignore and…
- `includePatterns` (string): Specify files to include using fast-glob patterns. Multiple patterns can be comma-separated (e.g., "**/*.{js,ts}", "src/**,docs/**"). Only matching files will be processed. Useful for focusing on spe…
- `outputPatterns` (array): Per-file inclusion levels. Patterns are evaluated in order and the first match wins; directoryStructureOnly takes precedence over compress, and a match with neither flag forces FULL content (use this…
- `style` (string): Output format style: xml (structured tags, default), markdown (human-readable with code blocks), json (machine-readable key-value), or plain (simple text with separators)
- `topFilesLength` (integer): Number of largest files by size to display in the metrics summary for codebase analysis (default: 10)

Output parameters:

- `description` (string): Human-readable description of the packing results
- `directoryStructure` (string): Tree structure of the processed directory
- `outputFilePath` (string): File path to the generated output file
- `outputId` (string): Unique identifier for accessing the packed content
- `result` (string): JSON string containing detailed metrics and file information
- `totalFiles` (number): Total number of files processed
- `totalTokens` (number): Total token count of the content

### `read_repomix_output` (~136 tokens)

Read Repomix Output

Read the contents of a Repomix-generated output file. Supports partial reading with line range specification for large files. This tool is designed for environments where direct file system access is limited (e.g., web-based environments, sandboxed applications). For direct file system access, use standard file operations.

Input parameters:

- `endLine` (number): Ending line number (1-based, inclusive). If not specified, reads to end.
- `outputId` (string, required): ID of the Repomix output file to read
- `startLine` (number): Starting line number (1-based, inclusive). If not specified, reads from beginning.

Output parameters:

- `content` (string): The file content or specified line range
- `endLine` (number): Ending line number used
- `linesRead` (number): Number of lines actually read
- `startLine` (number): Starting line number used
- `totalLines` (number): Total number of lines in the file

### `grep_repomix_output` (~185 tokens)

Grep Repomix Output

Search for patterns in a Repomix output file using grep-like functionality with JavaScript RegExp syntax. Returns matching lines with optional context lines around matches.

Input parameters:

- `afterLines` (number): Number of context lines to show after each match (like grep -A). Takes precedence over contextLines.
- `beforeLines` (number): Number of context lines to show before each match (like grep -B). Takes precedence over contextLines.
- `contextLines` (number): Number of context lines to show before and after each match (default: 0). Overridden by beforeLines/afterLines if specified.
- `ignoreCase` (boolean): Perform case-insensitive matching (default: false)
- `outputId` (string, required): ID of the Repomix output file to search
- `pattern` (string, required): Search pattern (JavaScript RegExp regular expression syntax)

Output parameters:

- `description` (string): Human-readable description of the search results
- `formattedOutput` (array): Formatted grep-style output with context lines
- `matches` (array): Array of search matches found
- `pattern` (string): The search pattern that was used
- `totalMatches` (number): Total number of matches found

### `pack_remote_repository` (~531 tokens)

Pack Remote Repository

Fetch, clone, and package a GitHub repository into a consolidated file for AI analysis. This tool automatically clones the remote repository, analyzes its structure, and generates a comprehensive report. Supports multiple output formats: XML (structured with <file> tags), Markdown (human-readable with ## headers and code blocks), JSON (machine-readable with files as key-value pairs), and Plain text (simple format with separators). Also supports various GitHub URL formats. Files matching known secret formats are excluded, but that scan is a heuristic, not an access boundary.

Input parameters:

- `compress` (boolean): Enable Tree-sitter compression to extract essential code signatures and structure while removing implementation details. Reduces token usage by ~70% while preserving semantic meaning. Generally not n…
- `ignorePatterns` (string): Specify additional files to exclude using fast-glob patterns. Multiple patterns can be comma-separated (e.g., "test/**,*.spec.js", "node_modules/**,dist/**"). These patterns supplement .gitignore and…
- `includePatterns` (string): Specify files to include using fast-glob patterns. Multiple patterns can be comma-separated (e.g., "**/*.{js,ts}", "src/**,docs/**"). Only matching files will be processed. Useful for focusing on spe…
- `outputPatterns` (array): Per-file inclusion levels. Patterns are evaluated in order and the first match wins; directoryStructureOnly takes precedence over compress, and a match with neither flag forces FULL content (use this…
- `remote` (string, required): GitHub repository URL or user/repo format (e.g., "yamadashy/repomix", "https://github.com/user/repo", or "https://github.com/user/repo/tree/branch")
- `style` (string): Output format style: xml (structured tags, default), markdown (human-readable with code blocks), json (machine-readable key-value), or plain (simple text with separators)
- `topFilesLength` (integer): Number of largest files by size to display in the metrics summary for codebase analysis (default: 10)

Output parameters:

- `description` (string): Human-readable description of the packing results
- `directoryStructure` (string): Tree structure of the processed repository
- `outputFilePath` (string): File path to the generated output file
- `outputId` (string): Unique identifier for accessing the packed content
- `result` (string): JSON string containing detailed metrics and file information
- `totalFiles` (number): Total number of files processed
- `totalTokens` (number): Total token count of the content

### `generate_skill` (~382 tokens)

Generate Claude Agent Skill

Generate a Claude Agent Skill from a local code directory. Creates a skill package containing SKILL.md (entry point with metadata) and references/ folder with summary.md, project-structure.md, files.md, and optionally tech-stacks.md.

This tool creates Project Skills in <project>/.claude/skills/<name>/, which are shared with the team via version control.

Output Structure:
  .claude/skills/<skill-name>/
  ├── SKILL.md                    # Entry point with usage guide
  └── references/
      ├── summary.md              # Purpose, format, and statistics
      ├── project-structure.md    # Directory tree with line counts
      ├── files.md                # All file contents
      └── tech-stacks.md          # Languages, frameworks, dependencies (if detected)

Example Path:
  /path/to/project/.claude/skills/repomix-reference-myproject/

Input parameters:

- `compress` (boolean): Enable Tree-sitter compression to extract essential code signatures and structure while removing implementation details (default: false).
- `directory` (string, required): Directory to pack (Absolute path)
- `ignorePatterns` (string): Specify additional files to exclude using fast-glob patterns. Multiple patterns can be comma-separated (e.g., "test/**,*.spec.js").
- `includePatterns` (string): Specify files to include using fast-glob patterns. Multiple patterns can be comma-separated (e.g., "**/*.{js,ts}", "src/**,docs/**").
- `skillName` (string): Name of the skill to generate (kebab-case, max 64 chars). Will be normalized if not in kebab-case. Used for the skill directory name and SKILL.md metadata. If omitted, auto-generates as "repomix-refe…

Output parameters:

- `description` (string): Human-readable description of the skill generation results
- `skillName` (string): Normalized name of the generated skill
- `skillPath` (string): Path to the generated skill directory
- `totalFiles` (number): Total number of files processed
- `totalTokens` (number): Total token count of the content

### `attach_packed_output` (~190 tokens)

Attach Packed Output

Attach an existing Repomix packed output file for AI analysis.
This tool accepts either a directory containing a repomix output file or a direct path to a packed repository file.
Supports multiple formats: XML (structured with <file> tags), Markdown (human-readable with ## headers and code blocks), JSON (machine-readable with files as key-value pairs), and Plain text (simple format with separators).
Calling the tool again with the same file path will refresh the content if the file has been updated.
It will return in that case a new output ID and the updated content.

Input parameters:

- `path` (string, required): Path to a directory containing repomix output file or direct path to a packed repository file (supports .xml, .md, .txt, .json formats)
- `topFilesLength` (integer): Number of largest files by size to display in the metrics summary (default: 10)

Output parameters:

- `description` (string): Human-readable description of the attached output
- `directoryStructure` (string): Tree structure extracted from the packed output
- `outputFilePath` (string): File path to the attached output file
- `outputId` (string): Unique identifier for accessing the packed content
- `result` (string): JSON string containing detailed metrics and file information
- `totalFiles` (number): Total number of files in the packed output
- `totalTokens` (number): Total token count of the content

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/yamadashy-repomix/repomix#diagnostics

## Score history

- 2026-09-24: 81
- 2026-09-23: 81
- 2026-09-22: 81
- 2026-09-21: 81

## Common questions

### What is the Repomix MCP server?

Repomix is an MCP server listed in the public MCP registry as io.github.yamadashy/repomix. Pack local or remote codebases into AI-friendly files that LLMs and coding agents can read or search. This page covers its npm package (repomix).

### Is the Repomix MCP server safe to use?

Repomix scores 81 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 24 September 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Repomix MCP server expose?

Repomix exposes 6 tools: pack_codebase, read_repomix_output, grep_repomix_output, pack_remote_repository, generate_skill, attach_packed_output. Their descriptions and schemas cost roughly 1,917 tokens of context every time the server is loaded.

### Is the Repomix MCP server still maintained?

Repomix is still listed as active in the MCP registry. We last reached this channel on 24 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Repomix MCP server under?

Repomix declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/repomix
- Socket report: https://socket.dev/npm/package/repomix
- Repository: https://github.com/yamadashy/repomix
- Website: https://repomix.com/
- Changelog RSS feed: https://verifymcp.io/servers/yamadashy-repomix/repomix.xml
- Changelog JSON feed: https://verifymcp.io/servers/yamadashy-repomix/repomix.json
- HTML version of this page: https://verifymcp.io/servers/yamadashy-repomix/repomix