Connect
Optimize
Secure
Attentive MCP Server
for AI Agents
Production-ready Attentive MCP server with extensible actions — plus built-in authentication, security, and optimized execution.
Attentive MCP Server
Built by 
StackOne
StackOne 
Coverage
19 Agent Actions
Create, read, update, and delete across Attentive — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Attentive MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Attentive 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 Attentive call.
Tools Discovery →What is the Attentive MCP Server?
A Attentive MCP server lets AI agents read and write Attentive data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Attentive MCP server ships with 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 Attentive MCP Tools and Actions
Every action from Attentive's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Custom Attributes
- Get Custom Attributes
Retrieve custom attributes for a user
- Set Custom Attributes
Store custom user attributes
Other (17)
- Add To Cart
Track when a user adds a product to their shopping cart
- Send Custom Event
Track custom business events
- Upload Product Catalog
Get a pre-signed S3 URL to upload your product catalog
- Add A Deletion Request
Add a CCPA data deletion request
- Create Or Update User With Attributes
Create or update a single user with attributes, subscriptions, and identifiers
- Get Me
Test authentication and retrieve company information
- Get Subscription
Get subscription eligibility for a user
- Get A CCPA Delete Request By Id
Get a CCPA delete request by Id
- Get Bulk Job Status
Retrieve status of a bulk ingestion job
- Subscribe User
Subscribe a user to receive communications
- Unsubscribe Subscriptions For A User
Unsubscribe a user from subscription type or channel
- Product View
Track when a user views a product
- Purchase
Track when a user generates an order or purchase
- View Recent Catalog Uploads
List recent catalog uploads with their statuses
- Lookup Product Catalog Ingestion
Get updated information on how the upload is progressing
- Identify User
Add a client user identifier or custom identifier(s) to a user
- Bulk Update User Attributes
Process bulk user attribute updates
Set Up Your Attentive MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Attentive 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>"
]
}
}
}Attentive 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
Attentive MCP Server FAQ
Attentive MCP server vs direct API integration — what's the difference?
A Attentive MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Attentive. A Attentive 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 Attentive at runtime. StackOne provides both.
How does Attentive authentication work for AI agents?
Attentive 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 Attentive account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Attentive MCP tools vulnerable to prompt injection?
Yes — Attentive 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 Attentive agent and how do I avoid it?
Context bloat happens when Attentive tool schemas and API responses eat your Attentive agent's memory, preventing it from reasoning effectively. A single Attentive 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 Attentive agent can access?
Yes — you can limit which actions your Attentive 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 Attentive MCP server?
Yes — you can create custom agent actions for your Attentive MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Attentive's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Attentive MCP server?
Skip a Attentive MCP server if your integration is purely software-to-software — direct Attentive 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 Attentive actions at runtime.
What AI frameworks and AI clients does the StackOne Attentive MCP server support?
The StackOne Attentive 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.