Log inSubmit server
Butterbase Oss logo

Butterbase Oss

by butterbase-ai

Manage Butterbase schemas, auth, functions, storage, RAG, deployments, and other backend features through MCP tools.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Butterbase Oss

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "mcp-285": {
      "command": "npx",
      "args": [
        "-y",
        "@butterbase/mcp"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

We couldn’t confirm it starts correctly

We ran the install command but it didn't respond within our test window — this can mean a slow first-time install rather than a real problem.

npx -y @butterbase/mcp

No response to initialize.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 7d ago.

Overview

butterbase-ai/butterbase-oss MCP server exposes Butterbase backend capabilities to AI agents through MCP tools. It connects to Butterbase's Postgres-backed runtime, including data, authentication, storage, functions, AI, RAG, and deployment surfaces. Run it over HTTP at `/mcp` or locally through the `@butterbase/mcp` stdio package. Reach for it when an agent needs to inspect or operate a Butterbase application without custom glue code.

Use cases

  • Manage application schemas and row-level security through an agent
  • Configure authentication, storage, functions, and webhooks
  • Deploy and operate Butterbase application components
  • Search RAG collections and configure AI services
  • Connect an MCP client to a self-hosted Butterbase backend

Key features

  • MCP tools for Butterbase backend operations
  • HTTP endpoint at /mcp
  • stdio support through @butterbase/mcp
  • Postgres schema and RLS management
  • Auth, storage, functions, AI, and RAG operations
  • Deployment and application management capabilities

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

13/13 checks healthy over the last 40d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 15d ago via OSV.dev · @butterbase/mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars3kStargazers on the source repository.
npm downloads113Package downloads in the last 30 days.
Last commit2d agoMost recent push to the default branch.
Install checkInconclusiveDidn't respond in our test window — often a slow first install.
Directory activity2 viewsConfig copies, upvotes, and views on AllMCPs.

How Butterbase Oss works

What butterbase-ai/butterbase-oss MCP server does

The butterbase-ai/butterbase-oss MCP server gives AI agents an MCP interface to Butterbase, an open-source backend-as-a-service built around Postgres. The repository describes the MCP surface as covering every capability exposed by the platform, rather than limiting agents to a single data or knowledge feature.

Through this interface, an agent can work with application schemas, row-level security, authentication, API keys, storage, serverless functions, realtime features, frontend and edge deployments, AI configuration, RAG collections, webhooks, audit logs, and other backend operations. The available scope depends on the Butterbase runtime and the capabilities implemented by the repository.

How it works

The MCP endpoint is available at /mcp over HTTP. For local process-based MCP clients, the repository provides the @butterbase/mcp package, which can be started with npx @butterbase/mcp. This gives an MCP-compatible client a tool interface instead of requiring the agent to construct separate API calls or application-specific glue code.

Butterbase itself supplies the underlying services: per-app Postgres databases, declarative schemas, automatic REST endpoints, RLS policies, S3/R2-backed object storage, Deno-based TypeScript functions, WebSocket subscriptions, AI gateway access, managed RAG, and related application operations. The MCP server acts as the agent-facing surface for those capabilities.

Setup and configuration

For a local stdio connection, use the published package with:

Terminal
npx @butterbase/mcp

For an HTTP connection, configure the MCP client to use the Butterbase /mcp endpoint.

The repository supports self-hosting the runtime data plane. It also describes a managed Butterbase offering; the MCP connection method and available operations may depend on which deployment you use.

Tools and capabilities

The butterbase-ai/butterbase-oss MCP server is intended to expose tools for backend administration and application operations, including:

  • Managing Postgres schemas, migrations, and row-level security policies.
  • Working with authentication settings, OAuth configuration, JWT behavior, and service keys.
  • Operating serverless functions, Durable Objects, realtime subscriptions, and webhooks.
  • Managing file storage, key-value data, audit logs, and frontend or edge deployments.
  • Configuring AI gateway behavior and using RAG ingestion, collections, search, and generated answers.
  • Working with agent workflows and MCP or function tools within Butterbase applications.
  • Performing supported app-management operations such as deployment and regional app moves.

The repository also includes a Claude Code plugin with guided skills and slash commands, but that plugin is separate from the MCP transport itself.

Limitations and notes

It also does not establish that every listed backend feature has identical support across self-hosted and managed deployments.

Butterbase's templates are separate application examples rather than additional MCP tools. Some managed-platform operations, such as cloning a template into an account, require a Butterbase account. For exact tool names and deployment-specific requirements, consult the repository documentation and setup files.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Butterbase Oss

butterbase-ai/butterbase-oss is an MCP server that connects AI agents to Butterbase's Postgres-backed backend. Its tools expose backend operations including schemas, row-level security, authentication, storage, serverless functions, AI gateway features, RAG, realtime, webhooks, and deployments through HTTP or stdio.

Run `npx @butterbase/mcp` to start the stdio server. For HTTP clients, connect to the Butterbase `/mcp` endpoint.

Yes, it can be used with Cursor through MCP because it provides a standard stdio server and an HTTP MCP endpoint.

It can expose Butterbase capabilities for schemas, RLS, auth, storage, functions, realtime, AI gateway services, RAG, webhooks, audit logs, and application deployment operations. The exact tool names and available operations depend on the Butterbase deployment.

Related MCP servers

All in Knowledge & Memory All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewButterbase Oss AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/mcp-285?style=directory)](https://allmcps.com/mcp/mcp-285)
HTML Embed
<a href="https://allmcps.com/mcp/mcp-285"><img src="https://allmcps.com/api/badge/mcp-285?style=directory" alt="Butterbase Oss on AllMCPs" /></a>