Skip to main content
Glama
Sign In
VibeSharing MCP Server

VibeSharing MCP Server

by erova
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

VibeSharing MCP Server

The missing link between your AI coding assistant and your team.

Note for anyone reading this on GitHub: erova/vibesharing-mcp is a read-only mirror, published automatically on each release. Pull requests against it will be overwritten by the next sync. To report a bug or request a change, please open an issue or write to hello@vibesharing.app.

Build prototypes with Claude Code, Cursor, or any AI tool — then instantly share them with your team for feedback. No context switching. No copy-pasting URLs. Just ship and collaborate.

Quick Start

1. Get Your Token

Sign up at vibesharing.app, then go to Account Settings to:

  • Copy your deploy token — starts with vs_

  • Connect your GitHub account (optional) — enables Push to Deploy

2. Connect Your Editor

Cursor / Windsurf / Claude Desktop (recommended — always up to date):

{
  "mcpServers": {
    "vibesharing": {
      "url": "https://vibesharing.app/api/mcp",
      "headers": {
        "Authorization": "Bearer vs_YOUR_TOKEN"
      }
    }
  }
}

Add to .cursor/mcp.json (Cursor) or ~/Library/Application Support/Claude/claude_desktop_config.json (Claude Desktop).

Claude Code:

claude mcp add vibesharing -s user \
  -e VIBESHARING_TOKEN=vs_YOUR_TOKEN \
  -- npx -y @vibesharingapp/mcp-server@latest

Then restart your editor. That's it.

3. Start Sharing

You: "Share this page on VibeSharing"
You: "Deploy this to the Product Redesign collection"
You: "What feedback came in on the dashboard?"

Related MCP server: Waystone

What You Can Do

Share a static HTML page instantly

"Share this HTML file on VibeSharing"

One command. No Vercel, no GitHub, no React wrapper. Your HTML page goes live with a feedback widget built in. CSS, SVGs, and images are auto-bundled into a self-contained file.

Deploy full projects

"Deploy this to VibeSharing in the Hero Use Cases collection as checkout-v3"

Claude confirms the collection, names the deployment, and handles everything — GitHub repo, deploy, team registration — in one conversation. Your first three prototypes are hosted on us; connect your own Vercel or Netlify account and the limit disappears.

Match your design system from the first prompt

"Build a settings page using our design system"

quick_prototype picks the right template from your org, hands the AI its CSS variables and written design instructions, and deploys — so the prototype is on-brand as it's generated, instead of built generic and retrofitted. Browse what's available with list_templates.

Go through feedback one person at a time

"What feedback did I get on the checkout flow?"
"Walk me through Jordan's comments"

On the local server, open feedback across your recent prototypes is summarized on the first VibeSharing tool call of a session — you find out something is waiting without asking. (Not yet on the remote endpoint.)

Asked without a name, get_feedback groups everything by author — "9 items from 4 people, 6 open" — instead of returning a wall of text. Asked with a name, it walks that person's comments one at a time, each carrying the page it was left on, the pinned position, the question it answered, the replies underneath, and the screenshot itself as an image — so you see what they saw rather than opening a link. You decide per comment whether to build it, skip it, or discuss — and close_feedback_loop tells the person what you did.

Keep every version, and branch safely

"Show me the version history"
"Fork this so I can try a dark variant"
"Roll back to v3"

Every deploy is a numbered version with its own immutable URL. fork_prototype copies one to a separate URL so you can explore without touching the original, and rollback_deploy restores any earlier version — for git-based and static prototypes alike.

Put it in front of customers

"Set up a study comparing these three variants"

create_campaign bundles several prototypes behind one gated portal with your own questions — star ratings, multiple choice, free text — and supports blind randomized A/B/C ordering so a name like "v2" can't skew a preference test. It lands as a draft; opening it and inviting the cohort stays a deliberate step in the dashboard.

Catch build failures before deploying

"Check this will build before we ship it"

validate_project looks for the things that actually break deploys — a missing framework dependency, no build script, conflicting configs — and returns fixes rather than a stack trace after the fact.

Keep context alive across sessions

"Sync my CLAUDE.md to VibeSharing"

Your project context persists on VibeSharing, so any team member (or AI session) can pick up where you left off. CLAUDE.md and AGENTS.md auto-sync on deploy.

Troubleshoot issues

"Run a VibeSharing health check"

The diagnose tool checks your token, GitHub connection, deploy locks, and recent errors — and auto-fixes what it can. If it can't fix something, send_support_request sends a detailed report to the admin.

Available Tools (31)

Tool

Description

Deploy & Share

quick_prototype

Idea to live URL in one step — picks a design system template, generates on-brand code, deploys

share_html

Share static HTML instantly — no hosting account, no GitHub. Auto-bundles CSS/SVGs/images.

deploy_files

Deploy multi-file projects to GitHub + your hosting provider with named deployments

deploy_prototype

Deploy a single code file directly

import_repo

Import a GitHub repo into VibeSharing

register_prototype

Register an already-deployed prototype by URL

validate_project

Check a project will build before deploying — missing frameworks, build scripts, conflicting configs

Design systems

list_templates

List your org's design system templates

get_template

Get a template's CSS variables, starter page, and AI design instructions — call before writing code

Organize

resolve_target

Fuzzy-match collections and projects — confirms where to deploy

create_collection

Create a new collection

list_prototypes

List/search all prototypes in your org

list_collections

List/search all collections

update_prototype

Rename a prototype or update its description and URL, in place

delete_prototype

Delete a prototype and its history — irreversible, creator or org admin only

Versions & variants

list_versions

Version history — version numbers, file counts, commit info, what can be rolled back

fork_prototype

Copy a prototype to its own URL to explore a variant; the original is untouched

rollback_deploy

Restore a previous version, for git-based and static prototypes

Research

create_campaign

Set up a customer study — several prototypes, your questions, optional blind A/B/C ordering

Feedback

get_feedback

Feedback grouped by author, or one person's comments as a queue with full context

triage_feedback

Update status, priority, or assignee on feedback

generate_feedback_topics

Create guided feedback questions for reviewers

close_feedback_loop

Resolve feedback with a note back to the stakeholder

Context

sync_context

Push CLAUDE.md, AGENTS.md, or project notes

upload_source

Upload source code to an existing prototype

add_context_link

Attach reference links (Figma, PRDs, docs)

list_context_links

List reference links on a collection or project

remove_context_link

Remove a reference link

Diagnostics

diagnose

Health check — token, GitHub, deploy locks, recent errors

send_support_request

Send a support request to the admin with context

verify_token

Check that your deploy token is valid

Remote vs Local

Remote (recommended): Connect to vibesharing.app/api/mcp. Always up to date, no installs, no cache issues. Works everywhere.

Local (advanced): Run via npx. Supports reading files from disk with file_path parameter. Requires Node.js 18+. May need npx clear-npx-cache after updates.

Environment Variables (local only)

Variable

Required

Description

VIBESHARING_TOKEN

Yes

Your deploy token from VibeSharing

VIBESHARING_URL

No

Custom API URL (defaults to https://vibesharing.app)

Learn More

Stop building in isolation. Start shipping with your team.

Available Tools

21 tools
add_context_linkA

Attach a reference link or note to a collection or project/prototype. Use this to add links to Figma designs, PRDs, Confluence docs, or free-text notes that provide context for reviewers.

Inputs: title (required), url, note, folder_id, +1 more.

close_feedback_loopA

CALL THIS AFTER DEPLOYING when there is open feedback. Matches what you just built to open feedback items, resolves them with explanations, and notifies the original stakeholders with a personalized digest. The stakeholder sees exactly what happened to their feedback.

Flow:

  1. Pull open feedback via get_feedback

  2. Look at what you built and match changes to feedback items

  3. Call this tool with the resolutions

  4. Stakeholders get email: 'Your feedback was addressed' with per-item explanations

Inputs: project_id (required), resolutions (required), deploy_url.

create_collectionA

Create a new collection in your VibeSharing organization. Collections group related projects and prototypes. Use this before deploying a prototype if you need a new collection to put it in.

Inputs: name (required), description.

deploy_filesA

Deploy a multi-file Next.js project to VibeSharing. Pushes files to GitHub, deploys to Vercel. Requires an existing prototype ID. For large files, use file_paths instead of files to read from disk and avoid MCP parameter size limits (~100KB). IMPORTANT: Before calling this, use resolve_target to confirm the target prototype with the user. If the user hasn't specified where to deploy, do NOT proceed — ask first.

Inputs: prototype_id (required), files, file_paths, deploy_name, +1 more.

deploy_prototypeA

Deploy code directly to VibeSharing. This deploys your code to Vercel and registers it as a prototype in one step. IMPORTANT: Before calling this, use resolve_target to confirm the collection, project name, and deploy name with the user. Do not deploy without user confirmation on where it should go.

Inputs: code (required), name (required), prototype_id.

diagnoseA

Run a comprehensive health check on the user's VibeSharing setup. Checks token validity, GitHub connection, stuck deploy locks (auto-clears them), recent deploy errors, and prototype status. Use this to troubleshoot issues.

Inputs: no named parameters.

generate_feedback_topicsA

Auto-generate feedback questions for a prototype based on what was built. IMPORTANT: Before generating questions, ask the user: 'What type of feedback is most important for this deploy?' and present these options:

  1. Awareness only — just sharing progress, no feedback needed

  2. Design direction — brand, visual, layout feedback

  3. Technical feasibility — is this buildable, are these features doable

  4. Vision alignment — does this match where we're going

  5. Interaction design — usability, flow, UX patterns

  6. Full review — all feedback welcome (default)

Use their answer as the 'focus' parameter. If 'awareness', skip topic generation and just set the brief. Otherwise generate 3-5 questions, weighting toward the chosen focus theme.

Inputs: project_id (required), brief, focus, topics.

get_feedbackA

Get feedback and comments for a specific prototype. Can filter by status (open, in_progress, resolved, wont_fix, deferred), priority (critical, high, medium, low), or assignee.

Inputs: project_id (required), status, priority, assigned_to.

import_repoA

Import an existing GitHub repo into VibeSharing. Pulls the code into a VibeSharing-hosted repo and deploys it to Vercel. IMPORTANT: Before calling this, use resolve_target to confirm the collection, project name, and deploy name with the user. Do not import without user confirmation on where it should go and what it should be called.

Inputs: repo_url (required), name, deploy_name, description, +3 more.

list_collectionsA

List all collections (folders) in your VibeSharing organization. Use this to find the collection_id when registering prototypes. Optionally filter by search query (fuzzy matched).

Inputs: search.

list_context_linksA

List all reference links and notes attached to a collection or project/prototype.

Inputs: folder_id, project_id.

list_prototypesA

List all prototypes in your VibeSharing organization. Shows name, URL, and recent activity. Optionally filter by search query (fuzzy matched).

Inputs: search.

register_prototypeA

Register a prototype on VibeSharing. Creates a standalone prototype by default. To add it as a version under an existing project, provide parent_project_id. IMPORTANT: Before calling this, use resolve_target to confirm the collection and project name with the user. Do not auto-generate names without user confirmation. Returns the VibeSharing URL where the team can view and leave feedback.

Inputs: name (required), description, source_code, external_url, +3 more.

remove_context_linkB

Remove a reference link or note by its ID.

Inputs: link_id (required).

resolve_targetA

CALL THIS BEFORE deploying or registering a prototype when the user hasn't provided exact IDs. Fuzzy-matches collection and project names, suggests where to put the prototype, and checks deploy_name availability. Returns structured options so you can confirm with the user before proceeding.

Inputs: deploy_name, project_name, collection_name.

send_support_requestA

Send a support request to the VibeSharing admin. Use this when the user has an issue you can't resolve, needs a configuration change, or wants to report a bug.

Inputs: subject (required), description (required), context.

share_htmlA

Share a static HTML page on VibeSharing — the simplest way to share. No Vercel, no GitHub, no React wrapper. Just uploads the HTML and gives you a shareable link with the feedback widget built in. Use this for standalone HTML files, one-page prototypes, or any static content that doesn't need a build step. For large HTML files, use file_path instead of html to avoid MCP parameter size limits.

Inputs: name (required), html, file_path, prototype_id, +1 more.

sync_contextB

Sync your CLAUDE.md, AGENTS.md, or project context to VibeSharing. This helps maintain context across AI sessions and team members.

Inputs: content (required), project_id (required).

triage_feedbackA

Update status, priority, or assignee on one or more feedback items. Use this to triage feedback from within your editor.

Inputs: feedback_ids (required), status, priority, assigned_to, +1 more.

upload_sourceA

Upload source code for an existing prototype on VibeSharing. Colleagues can then download the source from the prototype page. Use this when you want to share code without deploying it.

Inputs: source_code (required), prototype_id (required), filename, storage_option.

verify_tokenA

Verify that your VibeSharing deploy token is valid. Use this to check connectivity and authentication before other operations.

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

    TDQS

    A3.8/5.0

    Scored across 21 tools

    Disambiguation4/5

    Most tools have clearly distinct purposes (e.g., list vs. create vs. deploy vs. share), but the deploy/share family (deploy_prototype, deploy_files, share_html, import_repo) could be misselected without careful description reading. The descriptions are detailed enough to disambiguate, but the overlapping actions of deploying and registering create minor ambiguity.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun snake_case pattern (e.g., list_prototypes, create_collection, send_support_request). Even multi-word names like close_feedback_loop and generate_feedback_topics maintain the convention. No camelCase or mixed styles detected.

    Tool Count3/5

    With 21 tools, the server is at the 'heavy' end of the borderline range. While each tool appears to serve a distinct purpose, the count feels substantial for a typical MCP server, and an agent may need to scan many options before choosing.

    Completeness3/5

    The server covers a wide range of operations: authentication, deployment, sharing, feedback triage, context management, and diagnostics. However, there are notable gaps: no update or delete operations for prototypes or collections, and no get-by-ID function for prototypes. These limitations could force agents to work around them.

    Maintenance

    ActivitySlowing
    ResponsivenessNo recent community issues

    Resources

    Related MCP Connectors

    Related MCP Servers