Connect
Optimize
Secure
Live 53 Actions
Kustomer MCP Server
for AI Agents
Connect your AI agent to StackOne's Kustomer MCP server and give it 53 MCP tools out of the box. Auth, tool execution, and security all managed.
Kustomer MCP Server
Built by 
StackOne
StackOne 
Coverage
53 Agent Actions
Create, read, update, and delete across Kustomer — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Kustomer MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Kustomer 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 Kustomer call.
Tools Discovery →What is the Kustomer MCP Server?
A Kustomer MCP server lets AI agents read and write Kustomer data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Kustomer MCP server ships with 53 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 Kustomer MCP Tools
Every action from Kustomer's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Customers
- Create Customer
Create a new customer
- List Customers
Retrieve a paginated list of customers
- Update Customer
Update an existing customer by ID (full replacement)
- Delete Customer
Delete a customer by ID
Conversations
- Create Conversation
Create a new conversation associated with an existing customer
- List Conversations
Retrieve a paginated list of conversations
- Update Conversation
Update a conversation by replacing its fields (PUT semantics)
- Delete Conversation
Delete a conversation by ID
Messages
- Create Message
Create a new message. Requires channel, app (channel integration identifier — not a Kustomer ID), and direction. Use list_customers to get a customer ID and list_conversations to get a conversation ID if associating the message.
- List Messages
Retrieve a paginated list of messages
Message By IDs
- Get Message By ID
Retrieve a single message by ID
- Update Message By ID
Replace a message by ID using full PUT semantics (replaces entire resource; use update_message_attributes_by_id for partial PATCH updates)
User By IDs
- Get User By ID
Retrieve a single user by their unique ID
- Update User By ID
Update an existing org user's profile or account settings
Notes
- Create Note
Create a new note
- List Notes
Retrieve a paginated list of notes
Note By IDs
- Get Note By ID
Retrieve a single note by ID
- Update Note By ID
Replace a note by ID
- Delete Note By ID
Delete a note by ID
Klass By IDs
- Get Klass By ID
Retrieve a single klass by ID
- Update Klass By ID
Update an existing klass by ID
Klass
- Create Klass
Create a new klass
- Delete Klass
Delete a klass by ID
KObject (custom Object) By IDs
- Get KObject (custom Object) By ID
Retrieve a single kobject by klass name and ID. Use list_klasses to get the klass name and get_kobjects to get the kobject ID.
- Update KObject (custom Object) By ID
Update an existing kobject by klass name and ID. Use list_klasses to get the klass name and get_kobjects to get the kobject ID.
- Delete KObject (custom Object) By ID
Delete a kobject by klass name and ID. Use list_klasses to get the klass name and get_kobjects to get the kobject ID.
Sub-Status
- Update Sub-Status
Update an existing sub-status by ID
- Delete Sub-Status
Delete a sub-status by ID
Other (25)
- Create / Invite New User
Create an account for a new org user and send an invitation email
- Create KObject
Create a new kobject (custom object instance) within a klass. Use list_klasses to get the klass name (slug) required as a path parameter.
- Create Company
Create a new company
- Create Sub-status
Create a new sub-status
- Get Customer By ID
Retrieve a single customer by ID
- Get Conversation By ID
Retrieve a single conversation by ID
- Get Users
Retrieve a paginated list of org users
- Get Multiple Users By IDs
Retrieve multiple users by a comma-separated list of IDs
- Get Klasses
Retrieve a paginated list of klasses
- Get KObjects (custom Objects)
Retrieve a paginated list of kobjects for a klass. Use list_klasses first to get the klass name (slug) required as a path parameter.
- Get Companies
Retrieve a paginated list of companies
- Get Company By ID
Retrieve a single company by its unique ID
- Get Sub-statuses
Retrieve a paginated list of sub-statuses
- Get Sub-Status By ID
Retrieve a single sub-status by its unique ID
- Query Events Associated With Your Organization
Retrieve audit log events for your organization
- Update Customer Attributes
Partially update a customer's attributes by ID
- Update Conversation Attributes
Partially update a conversation's attributes using PATCH semantics
- Update Message Attributes By ID
Partially update message attributes by ID
- Update Note Attributes By ID
Partially update note attributes by ID
- Update Company Attributes
Update an existing company by ID
- Bulk Create Conversations
Create multiple conversations in a single request
- Bulk Batch Update Conversations
Update multiple conversations in a single request
- Bulk Delete Conversations
Delete multiple conversations in a single request
- Find Company KObjects (custom Objects)
Retrieve KObjects of a specific Klass associated with a company. Use list_companies to get the company ID and list_klasses to get the klass name.
- Find Customer KObjects (custom Objects)
Retrieve KObjects of a specific Klass associated with a customer. Use list_customers to get the customer ID and list_klasses to get the klass name.
Kustomer AI Agent Use Cases
Connect your AI agent to Kustomer and help your team scale the support operations they run by hand today.
Ticket Triage
Use StackOne to connect your AI agent to your helpdesk, CRM, and messaging tools to automate ticket triage and priority routing.
View Voice Call Summarization
Use StackOne to connect your AI agent to your telephony, CRM, and messaging tools to automate voice call summarization and CRM logging.
View Post-Demo Follow-Up
Use StackOne to connect your AI agent to your CRM, email, and calendar tools to automate post-demo follow-up.
ViewSet Up Your Kustomer MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Kustomer in under 10 lines of code.
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>"
]
}
}
}Check More Customer Support MCP Servers
Intercom
113+ actions
SurveyMonkey
104+ actions
Freshservice
84+ actions
ServiceNow
77+ actions
Freshdesk
73+ actions
Gorgias
69+ actions
Discourse
67+ actions
Platform 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
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 200+ Connector Builds Taught Us
MCP wraps APIs, it doesn't replace them. After building 200+ connectors that serve both, here's when each approach wins.
14 min read
Kustomer MCP Server FAQ
Does StackOne have a Kustomer MCP server?
Yes. StackOne offers a hosted Kustomer MCP server with 53 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.
Kustomer MCP server vs direct API integration — what's the difference?
A Kustomer MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Kustomer. A Kustomer 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 Kustomer at runtime. StackOne provides both.
How does Kustomer authentication work for AI agents?
Kustomer 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 Kustomer account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Kustomer MCP tools vulnerable to prompt injection?
Yes — Kustomer 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 Kustomer agent and how do I avoid it?
Context bloat happens when Kustomer tool schemas and API responses eat your Kustomer agent's memory, preventing it from reasoning effectively. A single Kustomer 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 Kustomer agent can access?
Yes — you can limit which actions your Kustomer 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 Kustomer MCP server?
Yes — you can create custom agent actions for your Kustomer MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Kustomer's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Kustomer MCP server?
Skip a Kustomer MCP server if your integration is purely software-to-software — direct Kustomer 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 Kustomer actions at runtime.
What AI frameworks and AI clients does the StackOne Kustomer MCP server support?
The StackOne Kustomer 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.