# io.github.MUSE-CODE-SPACE/vibe-coding (npm · vibe-coding-mcp)

Auto-document vibe coding sessions - collect, summarize, and publish

- Trust score: 65/100 (medium)
- Change this week: +22
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `vibe-coding-mcp`: 65/100 (this document), [markdown](https://verifymcp.io/servers/muse-code-space-vibe-coding/vibe-coding-mcp.md), [page](https://verifymcp.io/servers/muse-code-space-vibe-coding/vibe-coding-mcp)

## Channel facts

- Registry: `npm`
- Package: `vibe-coding-mcp`
- Version: `2.12.1`
- 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 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (141 of 143), 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 (141 of 143), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 27 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 55/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 3193 tokens (~212/item across 15 items; 15 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**: 99/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 98% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add muse-code-space-vibe-coding -- npx -y vibe-coding-mcp
```

### Codex

```bash
codex mcp add muse-code-space-vibe-coding -- npx -y vibe-coding-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "muse-code-space-vibe-coding": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "vibe-coding-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add muse-code-space-vibe-coding --command npx --arg -y --arg vibe-coding-mcp
```

### Hermes

```yaml
mcp_servers:
  muse-code-space-vibe-coding:
    command: "npx"
    args: ["-y", "vibe-coding-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "muse-code-space-vibe-coding": {
      "command": "npx",
      "args": [
        "-y",
        "vibe-coding-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.

### 2026-08-03 (score 65, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-08-02 (score 61, +56)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] Licence: MIT

### 2026-08-01 (score 5, −20)

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

### 2026-07-31 (score 25, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-27 (score 43)

First indexed and scored.

## MCP tools (15)

### `muse_collect_code_context` (~153 tokens)

Collects code blocks and conversation summaries into a structured context for documentation. Supports automatic language detection, duplicate removal, and statistics.

Input parameters:

- `autoDetectLanguage` (boolean): Automatically detect programming language (default: true)
- `codeBlocks` (array): Array of code blocks with language and code content
- `conversationSummary` (string, required): Summary of the conversation or context
- `includeStats` (boolean): Include code statistics in output (default: true)
- `rawText` (string): Raw text containing code blocks to extract (alternative to codeBlocks)
- `removeDuplicates` (boolean): Remove duplicate code blocks (default: true)
- `tags` (array): Optional tags for categorization (language tags auto-added)

### `muse_summarize_design_decisions` (~183 tokens)

Extracts and analyzes key architectural and design decisions from conversation logs. Supports both English and Korean, with importance scoring and keyword extraction. Set useAI=true for Claude-powered enhanced analysis.

Input parameters:

- `conversationLog` (string, required): The full conversation log text to analyze
- `extractRelatedCode` (boolean): Extract related code blocks (default: true)
- `includeImportanceScore` (boolean): Include importance scoring for each decision (default: true)
- `language` (string): Language of the conversation (default: auto-detect)
- `maxDecisions` (number): Maximum number of decisions to extract (default: 20)
- `projectContext` (string): Optional context about the project for better categorization
- `useAI` (boolean): Use Claude AI for enhanced analysis. Requires ANTHROPIC_API_KEY environment variable. (default: false)

### `muse_generate_dev_document` (~294 tokens)

Generates README, DESIGN, TUTORIAL, or CHANGELOG documents in Markdown format. Supports multiple languages, badges, API reference, FAQ, and more.

Input parameters:

- `apiReference` (array): API documentation
- `author` (string): Author name
- `badges` (array): Shield.io badges
- `codeContexts` (array): Array of code contexts to include
- `contributors` (array): List of contributors
- `customSections` (object): Custom sections to add (key: section title, value: content)
- `description` (string): Project or document description
- `designDecisions` (array): Array of design decisions to include
- `documentType` (string, required): Type of document to generate (README, DESIGN, TUTORIAL, CHANGELOG, API, ARCHITECTURE)
- `faq` (array): Frequently asked questions
- `features` (array): List of features
- `includeTableOfContents` (boolean): Whether to include a table of contents
- `installation` (object): Installation instructions
- `language` (string): Language for section headers (default: en)
- `license` (string): License type (e.g., MIT, Apache-2.0)
- `projectName` (string): Name of the project
- `repository` (string): Repository URL
- `title` (string): Title of the document
- `version` (string): Version number

### `muse_normalize_for_platform` (~77 tokens)

Converts Markdown documents for Notion, GitHub Wiki, or Obsidian platforms. Handles links, images, code blocks, tables, frontmatter, and platform-specific syntax.

Input parameters:

- `document` (string, required): The Markdown document to normalize
- `options` (object)
- `platform` (string, required): Target platform for the document

### `muse_publish_document` (~77 tokens)

Publishes generated documents to external platforms (Notion, GitHub Wiki, Obsidian, Confluence, Slack, or Discord).

Input parameters:

- `document` (string, required): The document content to publish
- `options` (object)
- `platform` (string, required): Target platform for publishing
- `title` (string, required): Title of the document

### `muse_create_session_log` (~101 tokens)

Creates daily or session-based vibe coding session logs.

Input parameters:

- `codeContexts` (array): Array of code contexts from the session
- `designDecisions` (array): Array of design decisions made
- `duration` (number): Session duration in seconds
- `options` (object)
- `summary` (string, required): Summary of what was accomplished
- `tags` (array): Tags for the session
- `title` (string, required): Title of the session

### `muse_analyze_code` (~149 tokens)

Performs deep code analysis using AST parsing. Extracts functions, classes, imports, and generates Mermaid diagrams. Supports AI-powered analysis for quality insights, security issues, and improvement suggestions.

Input parameters:

- `code` (string, required): The source code to analyze
- `diagramTypes` (array): Types of diagrams to generate (default: all)
- `filename` (string): Optional filename for context
- `generateDiagrams` (boolean): Generate Mermaid diagrams (default: true)
- `language` (string): Programming language (auto-detected if not provided)
- `useAI` (boolean): Enable AI-powered analysis for quality, security, and suggestions (default: false, requires ANTHROPIC_API_KEY)

### `muse_session_history` (~303 tokens)

Manages vibe coding session history. Save, retrieve, search, and manage past coding sessions with their code contexts and design decisions.

Input parameters:

- `action` (string, required): Action to perform: save (create new), get (retrieve by ID), update (modify existing), delete (remove), list (get all), search (find by keyword), stats (storage statistics)
- `codeContexts` (array): Array of code context objects
- `designDecisions` (array): Array of design decision objects
- `filterTags` (array): Filter by tags (for list)
- `keyword` (string): Search keyword (required for search action)
- `limit` (number): Maximum results to return (for list/search, default: 50)
- `metadata` (object): Additional metadata
- `offset` (number): Number of results to skip (for list, default: 0)
- `searchIn` (array): Fields to search in (for search, default: all)
- `sessionId` (string): Session ID (required for get, update, delete actions)
- `sortBy` (string): Sort field (for list, default: updatedAt)
- `sortOrder` (string): Sort order (for list, default: desc)
- `summary` (string): Session summary (required for save, optional for update)
- `tags` (array): Tags for categorization
- `title` (string): Session title (required for save, optional for update)

### `muse_export_session` (~224 tokens)

Exports vibe coding sessions to various formats (Markdown, JSON, HTML). Use for creating shareable documentation, backups, or reports from session history.

Input parameters:

- `bundleMultiple` (boolean): Combine multiple sessions into one document. Default: true
- `format` (string, required): Output format: markdown (readable docs), json (structured data), html (web page)
- `includeCodeBlocks` (boolean): Include code blocks from code contexts. Default: true
- `includeDesignDecisions` (boolean): Include design decisions. Default: true
- `includeMetadata` (boolean): Include session metadata (ID, timestamps, tags). Default: true
- `outputPath` (string): File path to save the export. If omitted, returns content directly.
- `sessionIds` (array): Specific session IDs to export. If omitted, exports all sessions.
- `template` (string): Template style: minimal (brief), default (balanced), detailed (comprehensive), report (formal)
- `title` (string): Document title. Default: "Vibe Coding Session Export"

### `muse_project_profile` (~322 tokens)

Manages project profiles for vibe coding sessions. Save project-specific settings for documentation, code analysis, and publishing.

Input parameters:

- `action` (string, required): Action: create, get, update, delete, list, setActive, getActive, clone
- `codeAnalysis` (object): Code analysis settings (defaultLanguage, defaultDiagramTypes, excludePatterns, useAI)
- `defaultTags` (array): Default tags applied to all sessions
- `description` (string): Profile description
- `documentation` (object): Documentation settings (defaultDocType, language, author, license, includeTableOfContents)
- `limit` (number): Max results for list (default: 50)
- `metadata` (object): Custom metadata
- `name` (string): Profile name (required for create, optional for get by name)
- `newName` (string): New name for cloned profile (required for clone)
- `offset` (number): Skip results for list (default: 0)
- `profileId` (string): Profile ID (for get, update, delete, setActive, clone)
- `projectPath` (string): Path to the project directory
- `publishing` (object): Publishing settings (defaultPlatform, platformSettings, autoPublish)
- `repository` (string): Git repository URL
- `sortBy` (string): Sort field for list
- `sortOrder` (string): Sort order for list
- `tagCategories` (array): Tag categories for organization
- `team` (object): Team information
- `version` (string): Project version

### `muse_git` (~503 tokens)

Git integration for vibe coding sessions. Get repository status, commit history, diffs, branch info. Capture git snapshots for sessions and extract design decisions from commit messages.

Input parameters:

- `action` (string, required): Action: status (repo state), log (commit history), diff (changes), branch (branch info), snapshot (full context), extractDecisions (from commits), linkToSession (attach to session)
- `author` (string): Filter commits by author name or email
- `contextLines` (number): Lines of context around changes (default: 3)
- `diffType` (string): Diff type: staged, unstaged, or all changes (default: all)
- `fromRef` (string): Source commit/branch/tag for diff
- `grep` (string): Search commit messages for keyword
- `includeDiff` (boolean): Include current diff in snapshot (default: true)
- `includeLog` (boolean): Include recent commits in snapshot (default: true)
- `includeRemote` (boolean): Include remote branches (default: true)
- `includeStash` (boolean): Include stash list in snapshot (default: false)
- `includeUntracked` (boolean): Include untracked files in status (default: true)
- `language` (string): Language for analysis (default: auto-detect)
- `limit` (number): Max commits to return for log/extractDecisions (default: 20, max: 500)
- `logLimit` (number): Commits to include in snapshot (default: 10)
- `oneline` (boolean): Compact log format (default: false)
- `path` (string): Filter by file or directory path
- `patterns` (array): Custom regex patterns for detecting design decisions
- `repoPath` (string): Path to git repository. Defaults to current working directory.
- `sessionId` (string): Session ID to link git context to (required for linkToSession)
- `since` (string): Filter commits after date (e.g., "2024-01-01", "1 week ago")
- `snapshotType` (string): Detail level when linking to session (default: minimal)
- `stat` (boolean): Include stat summary in diff (default: true)
- `toRef` (string): Target commit/branch/tag for diff
- `until` (string): Filter commits before date
- `verbose` (boolean): Include last commit info per branch (default: false)

### `muse_session_stats` (~174 tokens)

Provides analytics and insights about coding sessions. Actions: overview (summary stats), languages (language breakdown), timeline (activity over time), tags (tag analysis), productivity (work patterns), trends (compare periods).

Input parameters:

- `action` (string, required): Type of statistics to retrieve
- `compareWith` (string): Compare with previous period or average
- `format` (string): Output format (default: summary)
- `includeInsights` (boolean): Include AI-generated insights (default: true)
- `languages` (array): Filter by specific languages
- `period` (string): Time period for grouping (default: all)
- `since` (string): Start date for filtering (ISO date or relative like "1 week ago")
- `tags` (array): Filter by specific tags
- `until` (string): End date for filtering

### `muse_auto_tag` (~244 tokens)

Automatically suggests and applies tags to sessions. Actions: suggest (recommend tags), apply (add tags to session), train (learn from examples), config (configure tagging behavior).

Input parameters:

- `action` (string, required): Action to perform
- `categories` (array): Filter suggestions by category
- `codeBlocks` (array): Code blocks to analyze
- `content` (string): Text content to analyze for tags
- `customPatterns` (array): Custom patterns for tag detection (for config)
- `defaultCategories` (array): Default categories to use (for config)
- `enableAutoTag` (boolean): Enable/disable auto-tagging (for config)
- `examples` (array): Training examples for train action
- `includeExisting` (boolean): Include existing tags when applying (default: true)
- `maxTags` (number): Maximum number of tags to suggest (default: 5)
- `minConfidence` (number): Minimum confidence threshold 0-1 (default: 0.7)
- `sessionId` (string): Session ID to analyze or update (for suggest/apply)
- `useAI` (boolean): Use AI for tag suggestions (default: false)

### `muse_template` (~187 tokens)

Manages custom document templates with variable substitution. Actions: create, get, update, delete, list, apply (render with data), preview (render preview), import, export.

Input parameters:

- `action` (string, required): Action to perform
- `content` (string): Template content with {{variables}}
- `data` (object): Variable values for apply/preview
- `description` (string): Template description
- `filePath` (string): File path for import/export
- `filterType` (string): Filter list by type
- `format` (string): Import/export format (default: json)
- `limit` (number): Limit results for list
- `name` (string): Template name
- `offset` (number): Offset for list pagination
- `templateId` (string): Template ID
- `type` (string): Template type
- `variables` (array): Template variables definition

### `muse_batch` (~202 tokens)

Executes multiple tool operations in batch. Actions: execute (run batch), preview (plan without executing), status (check job status), cancel (stop running job), history (list past jobs). Supports sequential and parallel execution with dependency management.

Input parameters:

- `action` (string, required): Action to perform
- `includeErrors` (boolean): Include error details in response (default: true)
- `includeResults` (boolean): Include operation results in response (default: true)
- `jobId` (string): Job ID for status/cancel actions
- `limit` (number): Limit for history action (default: 20)
- `mode` (string): Execution mode (default: sequential)
- `operations` (array): Array of operations to execute
- `status` (string): Filter history by status
- `stopOnError` (boolean): Stop batch on first error (default: true)
- `timeout` (number): Timeout per operation in ms (default: 60000)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/muse-code-space-vibe-coding/vibe-coding-mcp#diagnostics

## Score history

- 2026-08-03: 65
- 2026-08-02: 61
- 2026-08-01: 5
- 2026-07-31: 25
- 2026-07-30: 43
- 2026-07-28: 43
- 2026-07-27: 43

## Links

- npm package: https://www.npmjs.com/package/vibe-coding-mcp
- Socket report: https://socket.dev/npm/package/vibe-coding-mcp
- Repository: https://github.com/MUSE-CODE-SPACE/vibe-coding-mcp
- Changelog RSS feed: https://verifymcp.io/servers/muse-code-space-vibe-coding/vibe-coding-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/muse-code-space-vibe-coding/vibe-coding-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/muse-code-space-vibe-coding/vibe-coding-mcp