Connect
Optimize
Secure
Live 37 Actions
Kameleoon MCP Server
for AI Agents
Connect your AI agent to StackOne's Kameleoon MCP server and give it 37 MCP tools out of the box. Auth, tool execution, and security all managed.
Kameleoon MCP Server
Built by 
StackOne
StackOne 
Coverage
37 Agent Actions
Create, read, update, and delete across Kameleoon — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Kameleoon MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Kameleoon 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 Kameleoon call.
Tools Discovery →What is the Kameleoon MCP Server?
A Kameleoon MCP server lets AI agents read and write Kameleoon data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Kameleoon MCP server ships with 37 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 Kameleoon MCP Tools
Every action from Kameleoon's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Experiments
- Create Experiment
Create a new A/B test experiment
- List Experiments
Retrieve a paginated list of all experiments
- Get Experiment
Retrieve a specific experiment by its ID
- Update Experiment
Update one or more fields of an existing experiment
- Delete Experiment
Permanently delete an experiment by its ID
Feature Flags
- Create Feature Flag
Create a new feature flag configuration
- List Feature Flags
Retrieve a paginated list of all feature flags
- Get Feature Flag
Retrieve a specific feature flag configuration by its ID
- Search Feature Flags
Search and filter feature flags with pagination
- Update Feature Flag
Update a feature flag configuration (full replacement)
- Delete Feature Flag
Permanently delete a feature flag configuration by its ID
Feature Flag Activity Logs
- Get Feature Flag Activity Logs
Retrieve activity logs for a specific feature flag
Feature Flag Environments
- Update Feature Flag Environment
Update a feature flag configuration for a specific environment
Feature Flag Rules
- Update Feature Flag Rule
Update a single targeting rule of a feature flag by rule ID
Goals
- Create Goal
Create a new goal with the specified parameters
- List Goals
Retrieve a paginated list of all goals
- Get Goal
Retrieve a specific goal by its ID
- Search Goals
Search and filter goals using flexible filtering conditions
- Update Goal
Update one or more fields of an existing goal
- Delete Goal
Permanently delete a goal by its ID
Segments
- Create Segment
Create a new targeting segment
- List Segments
Retrieve a paginated list of all segments
- Get Segment
Retrieve a specific segment by its ID
- Search Segments
Search and filter segments with pagination
- Update Segment
Update one or more fields of an existing segment
- Delete Segment
Permanently delete a segment by its ID
Personalizations
- Create Personalization
Create a new personalization campaign
- List Personalizations
Retrieve a paginated list of all personalizations
- Get Personalization
Retrieve a specific personalization by its ID
- Update Personalization
Update one or more fields of an existing personalization
- Delete Personalization
Permanently delete a personalization by its ID
Variations
- Create Variation
Create a new variation for an experiment
- List Variations
Retrieve a paginated list of all variations
- Get Variation
Retrieve a specific variation by its ID
- Search Variations
Search and filter variations with pagination
- Update Variation
Update one or more fields of an existing variation
- Delete Variation
Permanently delete a variation by its ID
Kameleoon AI Agent Use Cases
Connect your AI agent to Kameleoon and help your team scale the marketing operations they run by hand today.
Lead Nurture Sequences
Use StackOne to connect your AI agent to your marketing automation, CRM, and email tools to automate lead nurture email sequences.
View Campaign Performance Reports
Use StackOne to connect your AI agent to your marketing automation, email, and analytics platforms to automate campaign performance reporting.
View Content Repurposing
Use StackOne to connect your AI agent to your document stores, email platforms, and messaging tools to automate content repurposing and distribution.
ViewSet Up Your Kameleoon MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Kameleoon 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>"
]
}
}
}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
Kameleoon MCP Server FAQ
Does StackOne have a Kameleoon MCP server?
Yes. StackOne offers a hosted Kameleoon MCP server with 37 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.
Kameleoon MCP server vs direct API integration — what's the difference?
A Kameleoon MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Kameleoon. A Kameleoon 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 Kameleoon at runtime. StackOne provides both.
How does Kameleoon authentication work for AI agents?
Kameleoon 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 Kameleoon account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Kameleoon MCP tools vulnerable to prompt injection?
Yes — Kameleoon 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 Kameleoon agent and how do I avoid it?
Context bloat happens when Kameleoon tool schemas and API responses eat your Kameleoon agent's memory, preventing it from reasoning effectively. A single Kameleoon 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 Kameleoon agent can access?
Yes — you can limit which actions your Kameleoon 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 Kameleoon MCP server?
Yes — you can create custom agent actions for your Kameleoon MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Kameleoon's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Kameleoon MCP server?
Skip a Kameleoon MCP server if your integration is purely software-to-software — direct Kameleoon 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 Kameleoon actions at runtime.
What AI frameworks and AI clients does the StackOne Kameleoon MCP server support?
The StackOne Kameleoon 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.