Connect
Optimize
Secure
Netlify MCP Server
for AI Agents
Production-ready Netlify MCP server with 35 extensible actions — plus built-in authentication, security, and optimized execution.
Netlify MCP Server
Built by 
StackOne
StackOne 
Coverage
35 Agent Actions
Create, read, update, and delete across Netlify — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Netlify MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Netlify 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 Netlify call.
Tools Discovery →What is the Netlify MCP Server?
A Netlify MCP server lets AI agents read and write Netlify data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Netlify MCP server ships with 35 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 Netlify MCP Tools and Actions
Every action from Netlify's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Sites
- Create Site
Create a new site
- List Sites
List all sites for the authenticated user
- Get Site
Retrieve details for a specific site
- Update Site
Update an existing site
- Delete Site
Delete a site
Site Deploys
- Create Site Deploy
Create a new deploy for a site
- List Site Deploys
List all deploys for a site
- Get Site Deploy
Retrieve details for a specific site deploy
Site Build Hooks
- Create Site Build Hook
Create a new build hook for a site
- List Site Build Hooks
List all build hooks for a site
- Get Site Build Hook
Retrieve details for a specific build hook
- Update Site Build Hook
Update an existing build hook
- Delete Site Build Hook
Delete a build hook
DNS Zones
- Create DNS Zone
Create a new DNS zone
- Get DNS Zones
List all DNS zones for an account
- Get DNS Zone
Retrieve details for a specific DNS zone
- Delete DNS Zone
Delete a DNS zone
DNS Records
- Create DNS Record
Create a new DNS record
- Get DNS Records
List all DNS records for a zone
- Delete DNS Record
Delete a DNS record
Site Forms
- List Site Forms
List all forms for a site
- Delete Site Form
Delete a form from a site
Form Submissions
- List Form Submissions
List all submissions for a form
- Get Form Submission
Retrieve details for a specific form submission
Other (11)
- Get Current User
Retrieve the currently authenticated user
- List Accounts
List all accounts the user has access to
- Get Deploy
Retrieve details for a specific deploy
- Get Individual DNS Record
Retrieve details for a specific DNS record
- List Site Submissions
List all form submissions for a site
- Delete Submission
Delete a form submission
- Cancel Site Deploy
Cancel a running deploy
- Lock Deploy
Lock a deploy to prevent auto-publishing
- Unlock Deploy
Unlock a deploy to allow auto-publishing
- Restore Site Deploy
Restore a previous deploy as the current production deploy
- Rollback Site Deploy
Rollback site to the previous production deploy
Set Up Your Netlify MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Netlify 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>"
]
}
}
}More Developer Tools MCP Servers
Azure DevOps
172+ actions
Cloudflare
137+ actions
Bitbucket
134+ actions
Supabase
128+ actions
GitLab
125+ actions
Terraform
118+ actions
OneLogin
109+ actions
Netlify 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
Netlify MCP Server FAQ
Netlify MCP server vs direct API integration — what's the difference?
A Netlify MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Netlify. A Netlify 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 Netlify at runtime. StackOne provides both.
How does Netlify authentication work for AI agents?
Netlify 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 Netlify account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Netlify MCP tools vulnerable to prompt injection?
Yes — Netlify 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 Netlify agent and how do I avoid it?
Context bloat happens when Netlify tool schemas and API responses eat your Netlify agent's memory, preventing it from reasoning effectively. A single Netlify 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 Netlify agent can access?
Yes — you can limit which actions your Netlify 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 Netlify MCP server?
Yes — you can create custom agent actions for your Netlify MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Netlify's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Netlify MCP server?
Skip a Netlify MCP server if your integration is purely software-to-software — direct Netlify 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 Netlify actions at runtime.
What AI frameworks and AI clients does the StackOne Netlify MCP server support?
The StackOne Netlify 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.