Allows uploading, listing, inspecting metadata, deleting, and copying assets in Vercel Blob storage.
Click on "Install 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., "@assets-store-mcp upload my latest blog screenshot"
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.
MCP server for managing personal assets (images for blog posts, articles, etc.) in Vercel Blob storage.
Tool | Description |
| Upload a local file to your personal assets store, returns public URL |
| List files with optional prefix filter and pagination |
| Get metadata of an asset (size, content type, upload time) |
| Delete one or more assets by URL |
| Copy an asset to a new path |
Related MCP server: S3-Compatible 3D Storage MCP Server
Go to your Vercel dashboard → Storage → your Blob store → .env.local tab, and copy the BLOB_READ_WRITE_TOKEN.
Add to your .mcp.json:
{
"mcpServers": {
"assets-store": {
"command": "npx",
"args": ["-y", "assets-store-mcp"],
"env": {
"BLOB_READ_WRITE_TOKEN": "your_token_here"
}
}
}
}npm install
npm run dev # Run with tsx (no build needed)
npm run build # Compile TypeScriptTag a release to trigger automatic npm publish via GitHub Actions (OIDC, no token secret needed):
npm version patch # or minor / major
git push --follow-tagsThis server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP server for interacting with the Supabase platform
Butterbase MCP server — manage your backend: schemas, auth, functions, storage, RAG, deploys.
Cloud-hosted MCP server for durable AI memory
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/strzhao/vercel-blob-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server