Live 34 Actions

Lovable MCP Server
for AI Agents

Q: What AI frameworks and AI clients does the StackOne Lovable MCP server support?

The StackOne Lovable MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.

Connect your AI agent to StackOne's Lovable MCP server and give it 34 MCP tools out of the box. Auth, tool execution, and security all managed.

Start Free Book Demo Read Docs →

Lovable MCP Server

Built by

StackOne

Coverage

34 Agent Actions

Agents can read, write, delete and run operations in Lovable. Extend your agent's capabilities with custom actions.

MCP Actions → Build Actions →

Authentication

Agent Tool Authentication

Per-user OAuth in one call. Your Lovable MCP server gets session-scoped tokens with zero credentials stored on your infra.

Agent Auth →

Security

Agent Protection

Every Lovable tool response scanned for prompt injection in milliseconds, with 88.7% accuracy, all running on CPU.

Prompt Injection Defense →

Performance

Max Agent Context. Min Cost.

Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Lovable call.

Tools Discovery →

What is the Lovable MCP Server?

A Lovable MCP server lets AI agents read and write Lovable data through the Model Context Protocol, Anthropic's open standard for connecting LLMs to external tools. StackOne's Lovable MCP server ships with 34 pre-built actions, fully extensible via the Connector Builder, plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.

All Lovable MCP Tools

Every StackOne action for Lovable, ready for your agent. Read, write, delete and run operations, scoped to exactly what you need.

Projects

Publish Project
Build and deploy a Lovable project to its published URL.
List Projects
List Lovable projects in one or more workspaces.
Get Project
Get one Lovable project by id.
Update Project
Rename a Lovable project or change who can open it in the editor.
Delete Project
Delete a Lovable project.

Unified Groups

List Unified Groups
List unified groups in the Lovable workspace behind the API key.
Get Unified Group
Get a unified Lovable group by ID.

Unified Organizations

List Unified Organizations
List the Lovable workspace behind the API key.
Get Unified Organization
Get the Lovable workspace behind the API key by ID.

Unified Roles

List Unified Roles
List the workspace roles of a Lovable workspace.
Get Unified Role
Get a Lovable workspace role by ID.

Unified Users

List Unified Users
List unified users in the Lovable workspace behind the API key.
Get Unified User
Get a unified Lovable user by ID.

Workspace Members

Get Workspace Member
Get one accepted member of a Lovable workspace.
List Workspace Members
List the accepted members of a Lovable workspace.

Security Scans

List Security Scans
List the security scans of a Lovable project, newest first.
Get Security Scan
Get one Lovable security scan by id.

Workspaces

Get Workspace
Get one Lovable workspace by id.
List Workspaces
List the Lovable workspaces the API key can see.

Other (15)

Create Embed URL
Create a one-hour preview URL that shows a Lovable project in an iframe on one HTTPS origin.
Get Project Analytics
Get visitor traffic for a published Lovable project as an hourly or daily time series.
Get Project Analytics Breakdowns
Get the top pages, referrers, devices and countries for a published Lovable project.
Get Project Realtime Analytics
Get the live visitor counts of a published Lovable project.
Get Workspace Analytics
Get visitor traffic across a Lovable workspace as an hourly or daily time series.
Get Publish Status
Get the status of a Lovable publish started with publish_project.
List Workspace Groups
List the groups of a Lovable workspace.
List Project Collaborators
List the users individually granted access to a Lovable project.
List Security Scan Findings
List the findings of a Lovable security scan.
List Personal Data Findings
List the personal data (PII) findings detected in a Lovable project.
Get Workspace Security Insights
Get the Security Center overview of a Lovable workspace.
List Workspace Security Project Inventory
List a Lovable workspace's projects with their security review priority, finding counts, activity and publishing details.
Get User Info
Get the profile of the Lovable user who authorized the OAuth connection.
Update Publish Settings
Change who can open a published Lovable app without rebuilding it.
Unpublish Project
Take a published Lovable app offline.

Set Up Your Lovable MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to Lovable in under 10 lines of code.

MCP Clients

Agent Frameworks

Claude Desktop-

JSON

Claude Desktop Docs

{
  "mcpServers": {
    "stackone": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://api.stackone.com/mcp?x-account-id=<account_id>",
        "--header",
        "Authorization: Basic <YOUR_BASE64_TOKEN>"
      ]
    }
  }
}

Check More AI & ML MCP Servers

182+ actions

164+ actions

126+ actions

121+ actions

E2B

62+ actions

Dialpad

57+ actions

Pinecone

42+ actions

All AI & ML MCP Servers →

Platform Resources

Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery

Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.

10 min

Indirect Prompt Injection Defense for MCP Tools: A Technical Guide

MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.

12 min

MCP vs A2A: Architecture, Security, and When to Use Each

MCP vs A2A: what each protocol standardizes, how they differ, their shared security risks including indirect prompt injection, and when to use one, both, or a hybrid architecture.

12 min

MCP vs API: What Hundreds of Connector Builds Taught Us

MCP wraps APIs, it doesn't replace them. After building hundreds of connectors that serve both, here's when each approach wins.

14 min read

Lovable MCP Server FAQ

Does StackOne have a Lovable MCP server?

Yes. StackOne offers a hosted Lovable MCP server with 34 pre-built actions, and every action is tested and QA'd by StackOne. Connect it to Claude, Cursor, and any other MCP client, or to any agent framework through the AI Action SDK. It ships with managed agent authentication, prompt injection defense, and tool discovery with server-side execution that preserve your agent's context window and keep reasoning performance.

Lovable MCP server vs direct API integration: what's the difference?

A Lovable MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software work, where backend code calls Lovable. A Lovable MCP server is for AI agents that discover and call Lovable at runtime, such as MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI. StackOne provides both.

How does Lovable authentication work for AI agents?

Lovable authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK to get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Lovable account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.

Are Lovable MCP tools vulnerable to prompt injection?

Yes. Lovable MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content, such as documents, messages, tickets, records, or free-text fields, is a potential vector. StackOne Defender scans every tool response before it enters the agent's context. It runs regex patterns in ~1ms, then a MiniLM classifier in ~4ms. Accuracy is 88.7%, and it runs entirely on CPU.

What is the context bloat of a Lovable agent and how do I avoid it?

Context bloat happens when Lovable tool schemas and API responses eat your Lovable agent's memory, preventing it from reasoning effectively. A single Lovable query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery reduces it by loading only the tools relevant to each query.

Can I limit which actions my Lovable agent can access?

Yes. You can limit which actions your Lovable agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.

Can I create custom agent actions for my Lovable MCP server?

Yes. You can create custom agent actions for your Lovable MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Lovable's API, generate production-ready connector YAML, test against the live API, and validate before you ship.

When should I NOT use a Lovable MCP server?

Skip a Lovable MCP server if your integration is purely software-to-software, because direct Lovable API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Lovable actions at runtime.

What AI frameworks and AI clients does the StackOne Lovable MCP server support?

The StackOne Lovable MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.

Put your AI agents to work

All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.

Start Free Book Demo

Lovable MCP Serverfor AI Agents