Connect
Optimize
Secure
Announcing StackOne Defender: leading open-source prompt injection guard for your agent • Read More →
Production-ready Kit MCP server with 53 extensible actions — plus built-in authentication, security, and optimized execution.
Coverage
Create, read, update, and delete across Kit — and extend your agent's capabilities with custom actions.
Authentication
Per-user OAuth in one call. Your Kit MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →Security
Every Kit tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →Performance
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Kit call.
Tools Discovery →A Kit MCP server lets AI agents read and write Kit data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Kit MCP server ships with 53 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.
Every action from Kit's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Retrieve the color settings for the current account
Update the color settings for the current account
Draft or schedule a broadcast email to all or a subset of subscribers
Retrieve a paginated list of all broadcasts
Retrieve a specific broadcast by ID
Update an existing broadcast
Delete a broadcast by ID
Create a new custom field for subscribers
Retrieve all custom fields
Update a custom field label by ID
Delete a custom field by ID
Record a new purchase for a subscriber
Retrieve a paginated list of all purchases
Retrieve a specific purchase by ID
Create or update a subscriber (upsert)
Retrieve a specific subscriber by ID
Retrieve a paginated list of all subscribers
Update an existing subscriber by ID
Create a new tag
Retrieve a paginated list of all tags
Update a tag name by ID
Retrieve subscribers assigned to a specific tag
Add a tag to a subscriber by subscriber ID
Add an existing subscriber to a form by subscriber ID
Add an existing subscriber to a form by email address
Add an existing subscriber to a sequence
Add a subscriber to a sequence by email address
Retrieve the current Kit account and user information
Retrieve the creator profile for the current account
Retrieve email performance counts for the current account
Retrieve subscriber growth statistics for a specific time period
Retrieve performance statistics for a specific broadcast
Retrieve statistics for multiple broadcasts
Retrieve link click data for a specific broadcast
Retrieve all available email templates
Retrieve a paginated list of all forms
Retrieve subscribers who signed up through a specific form
Retrieve a paginated list of all segments
Retrieve a paginated list of all sequences
Retrieve subscribers enrolled in a specific sequence
Retrieve email statistics for a specific subscriber
Retrieve all tags assigned to a specific subscriber
Remove a tag from a subscriber by subscriber ID
Remove a tag from a subscriber by email address
Create multiple custom fields in a single request
Add multiple subscribers to forms in a single request
Create multiple subscribers in a single request
Unsubscribe a subscriber by ID
Filter subscribers based on email engagement metrics
Create multiple tags in a single request
Add a tag to a subscriber by email address
Apply tags to multiple subscribers in a single request
Remove tags from multiple subscribers in a single request
One endpoint. Any framework. Your agent is talking to Kit in under 10 lines of code.
MCP Clients
Agent Frameworks
{
"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>"
]
}
}
}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
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
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
origin_owner_id.All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.