Vibe Coding Documentation MCP (MUSE)
MUSE is a local-first MCP server that manages captured coding sessions, generates documentation and reports, analyzes code, and publishes or exports results.
Manage session history: save, get, update, delete, list, search, and view storage stats.
Create daily/session logs and export sessions as Markdown, JSON, or HTML.
Extract design decisions from English/Korean conversation logs, with optional Claude AI enhancement.
Analyze TypeScript/JavaScript/Python/Go code via AST, generate Mermaid diagrams, and optionally get AI quality/security suggestions.
Generate README, DESIGN, TUTORIAL, CHANGELOG, API, and ARCHITECTURE documents with badges, TOC, API reference, FAQ, and custom sections.
Normalize Markdown for Notion, GitHub Wiki, or Obsidian and publish to Notion, GitHub Wiki, Obsidian, Confluence, Slack, or Discord.
Integrate with Git for status, log, diff, branch, snapshot, decision extraction, and session linking.
Manage project profiles, custom templates, auto-tagging, session analytics, and batch tool operations.
Per README, also supports auto-capture hooks, session search resources, and prompts like /standup and /weekly-report.
Enables publishing of vibe coding documentation, design decisions, and generated developer documents to Confluence pages.
Supports publishing of code documentation, session logs, and design decisions to Discord channels.
Provides Git-based wiki updates for publishing README, DESIGN, TUTORIAL, CHANGELOG, API, and ARCHITECTURE documents to GitHub Wiki.
Offers full API integration for creating and publishing developer documentation, design decisions, and session logs as Notion pages in databases.
Enables local vault file storage with frontmatter support for saving generated documentation and coding session logs.
Allows publishing of vibe coding documentation, summaries, and session logs to Slack channels.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Vibe Coding Documentation MCP (MUSE) create a README for today's session and publish it to Notion"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
vibe-coding-mcp
Your AI coding sessions, documented automatically. Captures every Claude Code session from its transcript — prompts, files changed, commands, design decisions — then turns them into standups, weekly reports, ADRs and PR descriptions, and publishes them to Notion / Obsidian / GitHub Wiki / Confluence / Slack / Discord.
Why vibe-coding?
You spent four hours pair-programming with Claude. You made three architectural decisions, wrote eight files, and reverted twice. Tomorrow you will not remember why you picked the second option over the first. Most people solve this with manual journaling that lasts two weeks, or by trawling git log after the fact — and git log knows what changed, not why.
vibe-coding-mcp fixes that at the source. Claude Code already writes a full transcript of every session to ~/.claude/projects/. A tiny hook (vibe-coding-mcp hook) parses that transcript after every turn and stores a structured session locally: what you asked, which files were written or edited (with the code), which commands ran, how long it took, which branch, and the design decisions it can detect in the conversation. From there, 17 MCP tools turn those sessions into a standup, a weekly report, a daily log, a DESIGN / ADR / README / API doc, or a PR description, and publish them anywhere.
No API key needed for capture. Everything stays on your disk until you publish.
Related MCP server: Autonomous Documentation MCP
30-second install
# 1. Register the MCP server with Claude Code (tools, resources, slash-command prompts)
claude mcp add -s user vibe-coding-mcp -- npx -y vibe-coding-mcp
# 2. Install the capture hooks into ~/.claude/settings.json (backup written first)
npx -y vibe-coding-mcp init
# 3. Restart Claude Code. Then import the sessions you already have and check health
npx -y vibe-coding-mcp capture --all
npx -y vibe-coding-mcp doctorThen, inside Claude Code:
/standup → Yesterday / Today / Blockers from captured sessions
/weekly-report → Shipped / Decisions / In progress / Next, per project
/daily-vibe-log → today's sessions as one log, offer to publish
@vibe-coding://search/redis → every session that touched redis (titles, prompts, or file paths)Or just ask: "why did we choose JWT over sessions last week?", "document yesterday's session as a DESIGN doc and put it in my Obsidian vault", "write the PR description for this refactor".
Upgrading from v2.14? The old README's hook recipe used
claude mcp call, which is not a real Claude Code command, so nothing was ever captured. Runnpx vibe-coding-mcp initand remove the old entries. Seedocs/AUTO_CAPTURE.md.
What's new in v2.15.0
Auto-capture that works.
vibe-coding-mcp hookreads Claude Code's hook JSON on stdin, parses the session transcript, and upserts one session per Claude session (idempotent, exit 0 always, nothing on stdout).init/doctor/captureCLI. Install the hooks with a merge + backup, diagnose, backfill history.muse_digest. Standup / weekly / monthly report over captured sessions, grouped by day · project · tag, English or Korean.muse_capture_transcript. Capture on demand from inside the chat ("save this session").Resources
vibe-coding://sessions/today,vibe-coding://search/{query}and prompts/standup,/weekly-report.Agent Skill.
skills/vibe-coding/tells any skill-aware agent (Claude Code, Cursor, Codex, …) when and how to use the server.npm run skill:packbuilds the zip.
Real use cases
1. "Write my standup"
/standup calls muse_digest for yesterday and today plus muse_git status, and returns three bullet groups. Every bullet traces to a captured session title, file path, or decision — nothing invented.
2. "What did I ship this week?" (for your 1:1, Slack, or Notion)
/weekly-report calls muse_digest { period: "week", groupBy: "project" }: totals (sessions, hours, files, decisions), highlights (decisions with rationale), per-project sessions with the files they touched, and most-touched files. Optionally muse_publish_document to Notion / Slack.
3. "Why did we pick option B?"
@vibe-coding://search/<keyword> matches titles, summaries, tags and touched file paths. Open the session; designDecisions holds problem → choice → rationale, and summary holds the actual prompts you typed. This is the context a diff cannot give you.
4. "PR description for a refactor that touched 11 files"
/refactor-context chains session → muse_summarize_design_decisions → muse_analyze_code (AST + Mermaid) → muse_git diff into Why / What changed / Trade-offs / How to review.
5. "Fill my Obsidian vault with ADRs"
muse_summarize_design_decisions over a session, muse_generate_dev_document { documentType: "DESIGN" }, muse_publish_document { platform: "obsidian" } — frontmatter, tags and a session back-reference included.
Tools / Resources / Prompts
Name | Type | What it does |
| tool | (new) Claude Code transcript → stored session ( |
| tool | (new) Standup / weekly / monthly report over captured sessions, grouped by day / project / tag |
| tool |
|
| tool | Productivity dashboard: sessions/day, decisions/session, language breakdown |
| tool | Extract decisions (problem → options → choice → trade-off), EN/KO, optional Claude API |
| tool | AST analysis (TypeScript / Python / Go) + Mermaid diagrams |
| tool | README / DESIGN / TUTORIAL / CHANGELOG / API / ARCHITECTURE generator |
| tool | Daily or per-session log composition |
| tool | Export sessions to Markdown / JSON / HTML |
| tool | Markdown quirks for Notion / GitHub Wiki / Obsidian |
| tool | Publish to Notion / GitHub Wiki / Obsidian / Confluence / Slack / Discord |
| tool | Pull code blocks + summary out of raw text |
| tool |
|
| tool | Tag suggestions (Claude API, optional) |
| tool | Custom doc templates |
| tool | Per-project defaults (platform, tags, language) |
| tool | Several tool calls in one round-trip |
| resource | All captured sessions |
| resource | (new) Sessions started today, with files touched |
| resource | One session in full |
| resource | (new) Keyword search incl. file paths |
| resource | Which publish platforms are configured |
| prompt | Today's sessions → one daily log |
| prompt | (new) Yesterday / Today / Blockers |
| prompt | (new) Shipped / Decisions / In progress / Next |
| prompt | Session → dev document → publish |
| prompt | Session → PR description |
The skill
skills/vibe-coding/ is an Agent Skill (SKILL.md + references/ + scripts/setup.sh + assets/). It teaches the agent: check that capture is running before reporting, which tool chain matches which request, output shapes for standup / weekly / PR, and the rule that every reported line must trace to a captured session. Install it alongside the MCP server:
# Claude Code: drop it into your skills directory
cp -r skills/vibe-coding ~/.claude/skills/
# or build a zip for a marketplace (Agensi, etc.)
npm run skill:pack # → dist-skill/vibe-coding-skill-<version>.zipHow it works
Claude Code ──Stop / SessionEnd hook──▶ vibe-coding-mcp hook ──▶ ~/.vibe-coding-mcp/sessions/*.json
│ (stdin: session_id, │ parse ~/.claude/projects/<slug>/<id>.jsonl
│ transcript_path, cwd) │ prompts · files+code · commands · timing · decisions
│ │ upsert by claudeSessionId
▼
Claude (or any MCP client) ──▶ src/cli.ts ──▶ src/stdio.ts ─┐
src/index.ts (HTTP, POST /mcp) ─┴─▶ src/core/mcpServerFactory.ts
├─ toolRegistry.ts (17 muse_* tools)
├─ resources.ts (5 resources)
└─ prompts.ts (5 prompts)
│
▼
src/tools/*.ts · src/core/{captureEngine,transcriptParser}.ts
src/core/sessionStorage.ts · src/platforms/*.tsDesign choices that matter:
Capture reads the transcript, not the editor. Claude Code already logs everything; we parse it after the fact. The hook does no network calls, writes nothing to stdout, and exits 0 even on failure, so it can never slow down or break a session.
One session per Claude session. The
Stophook fires after every turn; captures are keyed onclaudeSessionIdand update in place. User-added tags survive updates.Local-first.
~/.vibe-coding-mcp/sessions/<id>.json. No DB, no telemetry.grep, back up, or sync it however you like.One registry, two transports. HTTP and stdio expose the same 17 tools / 5 resources / 5 prompts via
createMcpServer().
CLI reference
vibe-coding-mcp start the MCP server (stdio)
vibe-coding-mcp init install Stop + SessionEnd hooks into ~/.claude/settings.json
--project | --local target .claude/settings.json | .claude/settings.local.json
--dry-run | --print show merged file | print only the hooks block
--remove uninstall
--command "<cmd>" custom hook command
vibe-coding-mcp capture capture the newest transcript for the cwd
--all every transcript for the cwd (backfill)
--transcript <path> --cwd <dir> --dry-run --json
vibe-coding-mcp doctor hooks · transcripts · store · last hook run · platforms
vibe-coding-mcp hook (used by the hooks) stdin JSON → captureConfiguration
Env var | Required for | Purpose |
(none) | capture, digest, search, docs | Works with zero configuration |
|
| Claude-API-powered analysis |
| Notion publishing | |
| GitHub Wiki publishing | |
| Obsidian default vault | or pass |
| Confluence | |
| Slack / Discord | |
| — | Move the session store |
| — | If Claude Code's config is not in |
| HTTP mode only | default |
Tools that need an unconfigured integration return a structured INTEGRATION_NOT_CONFIGURED error instead of crashing.
Known limitations
Claude Code only (for now). Capture parses Claude Code's transcript format. Cursor / Codex transcripts are on the roadmap. The MCP tools themselves work from any MCP client.
Decision extraction is heuristic unless
useAI: truewith an API key: it looks for "decided / chose / instead of / because" patterns in EN and KO.AST analysis covers TS / Python / Go.
Publishing is one-way. Edits made in Notion / Wiki are not pulled back.
Single-user store. Team search across everyone's sessions needs a shared store (roadmap).
When NOT to use this
Automatic commit messages → use aicommits or similar; this generates documents.
Team-wide search across everyone's sessions → build a Notion DB on top, or wait for the shared store.
Hand-written rich notes → use Obsidian / Notion directly; this is capture-then-publish.
Roadmap
Cursor / Codex CLI transcript capture.
Shared session store (S3 / Git / WebDAV) and team mode.
prepare-commit-msgsuggestions from the current session's decisions.Rust / Swift / Kotlin AST + diagrams.
Contributing
git clone https://github.com/MUSE-CODE-SPACE/vibe-coding-mcp
cd vibe-coding-mcp
npm install
npm run typecheck && npm test && npm run build
node dist/cli.js capture --dry-run # try the capture engine on your own transcriptAdding a tool is one file in src/tools/<name>.ts, a Zod schema in src/core/schemas.ts, and one entry in src/core/toolRegistry.ts. CI runs typecheck + build + tests on Node 22 and 24.
Security
Paths are validated, filenames sanitized, webhook URLs must be HTTPS and allowlisted, outbound HTTP has timeouts and backoff — see src/core/security.ts and SECURITY.md. The capture hook stores only your prompts, the assistant's prose, the code it wrote, and the commands it ran; tool outputs, sub-agent side-chains and system reminders are dropped.
Report vulnerabilities privately via a GitHub Security Advisory: https://github.com/MUSE-CODE-SPACE/vibe-coding-mcp/security/advisories/new.
License
MIT — see LICENSE.
Maintainer
@yoon-k (MUSE-CODE-SPACE). Issues + support: https://github.com/MUSE-CODE-SPACE/vibe-coding-mcp/issues.
한국어 요약
vibe-coding-mcp는 Claude Code 세션을 자동으로 문서화하는 MCP 서버 + 에이전트 스킬입니다. Claude Code가 남기는 트랜스크립트(~/.claude/projects/)를 훅이 매 턴마다 파싱해서 프롬프트 · 수정한 파일과 코드 · 실행한 명령 · 소요 시간 · 브랜치 · 설계 결정을 ~/.vibe-coding-mcp/sessions/에 저장합니다. API 키 없이 동작하고, 발행하기 전까지는 아무것도 외부로 나가지 않습니다.
claude mcp add -s user vibe-coding-mcp -- npx -y vibe-coding-mcp # MCP 등록
npx -y vibe-coding-mcp init # 훅 설치 (settings.json 백업 후 병합)
npx -y vibe-coding-mcp capture --all # 기존 세션 가져오기
npx -y vibe-coding-mcp doctor # 상태 확인Claude Code 안에서 /standup(어제·오늘·블로커), /weekly-report(주간 보고, language: ko 지원), /daily-vibe-log, @vibe-coding://search/키워드를 바로 쓸 수 있고, "지난주에 왜 JWT를 골랐지?", "어제 세션을 DESIGN 문서로 만들어서 Obsidian에 넣어줘", "이 리팩터링 PR 설명 써줘" 같은 요청에 muse_* 도구 17개가 대응합니다.
v2.14의 훅 레시피(
claude mcp call)는 존재하지 않는 명령이라 실제로 캡처가 되지 않았습니다. v2.15에서init으로 교체하세요.
설치·검증·백필은 docs/AUTO_CAPTURE.md, 변경 이력은 CHANGELOG.md, 스킬 패키지는 skills/vibe-coding/ 참고.
Available Tools
15 toolsmuse_analyze_codeA
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.
Inputs: code (required), language, filename, generateDiagrams, +2 more.
muse_auto_tagC
Automatically suggests and applies tags to sessions. Actions: suggest (recommend tags), apply (add tags to session), train (learn from examples), config (configure tagging behavior).
Inputs: action (required), sessionId, content, codeBlocks, +9 more.
muse_batchA
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.
Inputs: action (required), operations, mode, stopOnError, +6 more.
muse_collect_code_contextB
Collects code blocks and conversation summaries into a structured context for documentation. Supports automatic language detection, duplicate removal, and statistics.
Inputs: conversationSummary (required), codeBlocks, rawText, tags, +3 more.
muse_create_session_logC
Creates daily or session-based vibe coding session logs.
Inputs: title (required), summary (required), codeContexts, designDecisions, +3 more.
muse_export_sessionA
Exports vibe coding sessions to various formats (Markdown, JSON, HTML). Use for creating shareable documentation, backups, or reports from session history.
Inputs: format (required), sessionIds, outputPath, includeMetadata, +5 more.
muse_generate_dev_documentB
Generates README, DESIGN, TUTORIAL, or CHANGELOG documents in Markdown format. Supports multiple languages, badges, API reference, FAQ, and more.
Inputs: documentType (required), title, projectName, description, +15 more.
muse_gitB
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.
Inputs: action (required), repoPath, includeUntracked, limit, +21 more.
muse_normalize_for_platformA
Converts Markdown documents for Notion, GitHub Wiki, or Obsidian platforms. Handles links, images, code blocks, tables, frontmatter, and platform-specific syntax.
Inputs: document (required), platform (required), options.
muse_project_profileB
Manages project profiles for vibe coding sessions. Save project-specific settings for documentation, code analysis, and publishing.
Inputs: action (required), profileId, name, newName, +15 more.
muse_publish_documentB
Publishes generated documents to external platforms (Notion, GitHub Wiki, Obsidian, Confluence, Slack, or Discord).
Inputs: document (required), title (required), platform (required), options.
muse_session_historyC
Manages vibe coding session history. Save, retrieve, search, and manage past coding sessions with their code contexts and design decisions.
Inputs: action (required), sessionId, title, summary, +11 more.
muse_session_statsA
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).
Inputs: action (required), since, until, period, +5 more.
muse_summarize_design_decisionsA
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.
Inputs: conversationLog (required), projectContext, language, includeImportanceScore, +3 more.
muse_templateC
Manages custom document templates with variable substitution. Actions: create, get, update, delete, list, apply (render with data), preview (render preview), import, export.
Inputs: action (required), templateId, name, type, +9 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 15 tools
Most tools have clearly distinct purposes, but there is minor overlap among muse_create_session_log, muse_export_session, and muse_session_history, which all deal with session records. Also, muse_collect_code_context and muse_analyze_code both involve code but serve different goals.
The tools follow a consistent muse_verb_noun pattern for most names (e.g., analyze_code, create_session_log). However, 'muse_git' uses a noun instead of a verb-noun, and 'muse_batch' lacks a specific object, causing slight inconsistency.
With 15 tools, the count sits at the upper bound of the ideal range (3-15). Each tool serves a distinct function within the documentation domain, so it's still well-scoped, though a few could potentially be merged.
The tool set covers code analysis, session management, documentation generation, publishing, templates, and git integration, providing a comprehensive workflow. Minor gaps exist, such as no explicit tool for deleting sessions or documents, but the core lifecycle is addressed.
Maintenance
Related MCP Connectors
Shared project docs, task planning and GitHub evidence for people and their AI agents.
Versioned documentation registry and semantic search for AI tools and coding assistants.
Shared memory for coding agents. Stop re-explaining your codebase every session.
Serves your design system and coding standards to coding agents, so they stop guessing.
Related MCP Servers
- -licenseBqualityNot gradedmaintenanceAutomates the creation of standardized documentation by extracting information from source files and applying templates, with integration capabilities for GitHub, Google Drive, and Perplexity AI.33-
- AlicenseAqualityDmaintenanceAutomatically analyzes codebases and generates beautiful Mintlify-style documentation with API references, code examples, and changelogs. Keeps documentation synchronized with code changes across multiple programming languages.81MIT
- AlicenseNot gradedqualityDmaintenanceAutomatically generates comprehensive wiki documentation from any codebase, including Mermaid diagrams, source code citations, and automated quality checks.3MIT
- AlicenseNot gradedqualityDmaintenanceAnalyzes codebases to automatically generate README, API docs, architecture diagrams, and CHANGELOG.MIT