Yocoolab MCP server
Pin visual feedback on any live web page and send it to Claude Code, Cursor or your AI agent.
1 stars55 downloads/wk
Reviews
Write oneNobody has reviewed Yocoolab yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Yocoolab tools (18, 3 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
add_thread_messageAdd a message to a feedback thread without changing its status. Use this to post updates like preview URLs, implementation notes, or questions back to the thread.
ai_analyze_pageAsk the Yocoolab AI assistant to analyze a web page. Supports text questions with optional screenshot (vision) and page context. Useful for getting AI insights about a page layout, accessibility, or code structure.
create_pr_for_threadwrite actionCreate a GitHub pull request (or add a commit to the existing working branch) with code changes that address a feedback thread. All fixes for a repo accumulate on a single working branch with one PR.
get_activity_summaryGet a high-level summary of Claude Code activity: total events, active sessions, tool usage breakdown, files touched, and error count.
get_ai_conversationsList recent AI assistant conversations. Returns conversation IDs, page URLs, and message counts.
get_companion_messagesCheck for new messages from the AI Companion panel in the Chrome extension. Returns pending messages and clears the queue. Each message includes the user text, page context, and optional screenshot/element attachments.
get_dashboard_urlGet the URL for the real-time activity monitoring dashboard. Open in a browser to see live Claude Code activity, tool usage charts, and session timelines.
get_deployment_previewCheck if a preview deployment is available for a specific repo and branch. Returns the preview URL if deployed. Useful after creating a PR to get the live preview link.
get_files_touchedList all files that have been read, written, or edited across Claude Code sessions. Shows file paths with session counts.
get_recent_eventsGet the most recent Claude Code activity events (tool calls, prompts, errors). Shows timestamps, tool names, and key details.
get_thread_contextGet full details of a feedback thread including all messages, UI element context (selector, coordinates, element tag), view state, and the annotated screenshot. The screenshot is returned as an image so you can visually see the feedback location.
list_open_threadsList open feedback threads. Omit repo to get ALL threads across every repo you have access to — each result is labeled with its repo, change type (frontend/api/backend), board stage, and UI element context. Use claude_code_pending=true to only show threads that users have sent to Claude Code.
mark_thread_addressedMark a feedback thread as addressed and ready for review. This moves the thread to the "In Review" column and clears the pending flag — it does NOT resolve or close the thread. Only a human closes a thread (after verifying the change). Optionally add a message explaining what you did.
pendo_get_feature_usageQuery Pendo for feature usage analytics (click events, unique visitors) over a time range. Useful for understanding how heavily a feature is used when reviewing feedback threads.
pendo_get_page_analyticsQuery Pendo for page-level analytics (page views, unique visitors, avg time on page). Use the page_url from thread context to check how popular a page is.
pendo_list_guidesList active in-app guides from Pendo. Optionally filter by page URL to see what guides are deployed on a specific page.
pendo_track_eventwrite actionSend a custom track event to Pendo. Use this to track actions like feedback resolved, PR created from feedback, or guide suggestions.
reply_to_companionwrite actionSend a reply back to the AI Companion panel in the Chrome extension. The reply will appear as an assistant message in the companion chat UI. Supports Markdown formatting.
Public scan report
scanner v0.1.9 · 2026-09-20 · same rubric, same numbers if you re-run it
- Code scan77 source files scanned13/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancelast push 12 days ago15/15
- Maintainer identitynamespace and repository owner differ4/10
Findings (1)
- highShell command built from a string (injection risk)
exec.shell-concatdist/commands/setup.js: …child_process'); const result = execSync(`pgrep -f "${name}" 2>/dev/null || true`, { encoding:…
Install directly
Runs npx -y @yocoolab/mcp-server on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add yocoolab -- npx -y @yocoolab/mcp-server
Yocoolab: common questions
- Is Yocoolab MCP server safe?
- With care: it is graded C, so read the findings first (58/100). Read the Yocoolab safety report
- How do I install Yocoolab?
- It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
- Does Yocoolab need an API key?
- Yes. The registry entry asks for
YOCOOLAB_TOKEN,GITHUB_TOKEN. - Is Yocoolab maintained?
- The last commit was 13 days ago (2026-09-07). The latest release is v2.4.3.
- What can I use instead of Yocoolab?
- Servers from other publishers that do the same job: Agent-Native Plan MCP server, Google Surf MCP server and PDF MCP server. Compare all Yocoolab alternatives.
Alternatives to Yocoolab
Same job from other publishers: the closest match first, then the best rated.
- Agent-Native PlanStructured visual plans and PR recaps with diagrams, prototypes, annotations, and sharingnot reviewedEstablishedA
- Google SurfWeb, academic and code search with graph RAG, data lineage, ontology and cross-project schema links.not reviewedEstablishedB
- PDFAgentic RAG over one PDF or a whole folder: hybrid search, selective page reads, tables, OCR.not reviewedEstablishedA
- You.com Web Access & AIWeb search, AI agent, and content extraction via You.com APIsnot reviewedEstablishedA
- Mellos MappingLive layered dependency map for bottom-up development, drawn by the agent in a terminal pane.not reviewedEstablishedA