Connect
Optimize
Secure
Retool MCP Server
for AI Agents
Production-ready Retool MCP server with 44 extensible actions — plus built-in authentication, security, and optimized execution.
Retool MCP Server
Built by 
StackOne
StackOne 
Coverage
44 Agent Actions
Create, read, update, and delete across Retool — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Retool MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Retool 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 Retool call.
Tools Discovery →What is the Retool MCP Server?
A Retool MCP server lets AI agents read and write Retool data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Retool MCP server ships with 44 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 Retool MCP Tools and Actions
Every action from Retool's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Custom Component Librarys
- Create Custom Component Library
Create a new custom component library
- Get Custom Component Library
Get a custom component library by ID
Folders
- Create Folder
Create a new folder
- List Folders
Get all folders in the organization
- Get Folder
Get a folder by ID
- Update Folder
Update a folder by ID
- Delete Folder
Delete a folder by ID
Groups
- Create Group
Create a new permission group
- List Groups
Get all permission groups
- Get Group
Get a group by ID
- Update Group
Update a group using JSON Patch
- Delete Group
Delete a permission group
Resources
- List Resources
Get all resources in the organization
- Delete Resource
Delete a resource by ID
Roles
- Create Role
Create a new role
- List Roles
Get all roles in the organization
- Update Role
Update a role by ID
- Delete Role
Delete a role by ID
Spaces
- Create Space
Create a new child space
- List Spaces
Get all child spaces
- Get Space
Get a space by ID
- Update Space
Update a space by ID
- Delete Space
Delete a space by ID
User Invites
- Create User Invite
Create a new user invite
- List User Invites
Get all user invites in the organization
- Get User Invite
Get a user invite by ID
- Delete User Invite
Delete a user invite by ID
Users
- Create User
Create a new user in the organization
- List Users
Get all users in the organization
- Get User
Get a specific user by ID
- Update User
Update a user by ID
- Delete User
Disable a user from the organization
Workflows
- List Workflows
Get all workflows in the organization
- Get Workflow
Get a workflow by ID
Other (10)
- Add Users To Group
Add users to a permission group
- Copy Elements To Another Space
Copy apps, queries, resources, and workflows to another space
- Add Or Update User Attribute
Add or update a user attribute
- Add User Invites To Group
Add user invites to a group
- List Custom Component Libraries
Get all custom component libraries in the organization
- List Custom Component Library Revisions
Get all revisions of a custom component library
- Get Custom Component Library Revision Files
Get all files for a custom component library revision
- Get Workflow Run
Get details for a workflow run
- Remove User From Group
Remove a user from a permission group
- Remove User Invite From Group
Remove a user invite from a group
Set Up Your Retool MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Retool 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
Retool 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
Retool MCP Server FAQ
Retool MCP server vs direct API integration — what's the difference?
A Retool MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Retool. A Retool 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 Retool at runtime. StackOne provides both.
How does Retool authentication work for AI agents?
Retool 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 Retool account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Retool MCP tools vulnerable to prompt injection?
Yes — Retool 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 Retool agent and how do I avoid it?
Context bloat happens when Retool tool schemas and API responses eat your Retool agent's memory, preventing it from reasoning effectively. A single Retool 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 Retool agent can access?
Yes — you can limit which actions your Retool 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 Retool MCP server?
Yes — you can create custom agent actions for your Retool MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Retool's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Retool MCP server?
Skip a Retool MCP server if your integration is purely software-to-software — direct Retool 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 Retool actions at runtime.
What AI frameworks and AI clients does the StackOne Retool MCP server support?
The StackOne Retool 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.