Connect
Optimize
Secure
Unbounce MCP Server
for AI Agents
Production-ready Unbounce MCP server with 23 extensible actions — plus built-in authentication, security, and optimized execution.
Unbounce MCP Server
Built by 
StackOne
StackOne 
Coverage
23 Agent Actions
Create, read, update, and delete across Unbounce — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Unbounce MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Unbounce tool response scanned for prompt injection in milliseconds — 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 Unbounce call.
Tools Discovery →What is the Unbounce MCP Server?
A Unbounce MCP server lets AI agents read and write Unbounce data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Unbounce MCP server ships with 23 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Cursor, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All Unbounce MCP Tools and Actions
Every action from Unbounce's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Accounts
- List Accounts
Retrieve all Unbounce accounts accessible to the authenticated user
- Get Account
Retrieve details for a specific Unbounce account by its ID
Pages
- List Pages
Retrieve all landing pages accessible to the authenticated user
- Get Page
Retrieve details and statistics for a specific Unbounce landing page
Page Leads
- Create Page Lead
Submit a new lead to a specific Unbounce landing page
- List Page Leads
Retrieve all lead submissions captured by a specific Unbounce landing page
- Get Page Lead
Retrieve a specific lead submission from an Unbounce landing page
- Delete Page Lead
Delete a specific lead submission from an Unbounce landing page
Page Lead Deletion Requests
- Create Page Lead Deletion Request
Create an async request to delete one or more leads for a specific Unbounce landing page
- Get Page Lead Deletion Request
Retrieve the status of an async lead deletion request for a specific Unbounce landing page
Other (13)
- List Account Sub-Accounts
Retrieve all sub-accounts belonging to a specific Unbounce account
- List Account Pages
Retrieve all landing pages belonging to a specific Unbounce account
- Get Domain
Retrieve details for a specific Unbounce custom domain
- List Domain Pages
Retrieve all landing pages published to a specific Unbounce custom domain
- Get Lead
Retrieve details for a specific Unbounce lead by its ID
- List Page Group Pages
Retrieve all landing pages belonging to a specific Unbounce page group
- List Page Form Fields
Retrieve all form fields configured on a specific Unbounce landing page
- Get Sub-Account
Retrieve details for a specific Unbounce sub-account by its ID
- List Sub-Account Domains
Retrieve all custom domains associated with a specific Unbounce sub-account
- List Sub-Account Page Groups
Retrieve all page groups within a specific Unbounce sub-account
- List Sub-Account Pages
Retrieve all landing pages within a specific Unbounce sub-account
- Get Self User
Retrieve the profile of the currently authenticated OAuth user
- Get User
Retrieve the profile of a specific Unbounce user by their ID
Set Up Your Unbounce MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Unbounce in under 10 lines of code.
MCP Clients
Agent Frameworks
JSON{
"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>"
]
}
}
}Unbounce MCP Server Resources
MCP Code Mode: Keeping Tool Responses Out of Agent Context
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
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
Unbounce MCP Server FAQ
Unbounce MCP server vs direct API integration — what's the difference?
A Unbounce MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Unbounce. A Unbounce MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Unbounce at runtime. StackOne provides both.
How does Unbounce authentication work for AI agents?
Unbounce authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Unbounce account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Unbounce MCP tools vulnerable to prompt injection?
Yes — Unbounce MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — 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 — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Unbounce agent and how do I avoid it?
Context bloat happens when Unbounce tool schemas and API responses eat your Unbounce agent's memory, preventing it from reasoning effectively. A single Unbounce query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Unbounce agent can access?
Yes — you can limit which actions your Unbounce 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 Unbounce MCP server?
Yes — you can create custom agent actions for your Unbounce MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Unbounce's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Unbounce MCP server?
Skip a Unbounce MCP server if your integration is purely software-to-software — direct Unbounce 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 Unbounce actions at runtime.
What AI frameworks and AI clients does the StackOne Unbounce MCP server support?
The StackOne Unbounce 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.