Skip to main content

Announcing StackOne Defender: leading open-source prompt injection guard for your agent • Read More →

Connect

Connectors Agent Auth MCP Connector Builder

Optimize

Tool Discovery Falcon Engine

Secure

Defender
Connectors

HRIS / HCM

Employee Onboarding Employee Offboarding

Recruiting

Application Screening Interview Scheduling

Customer Support

Ticket Triage Voice Call Summarization

Sales & CRM

Deal Risk Scoring Lead Qualification

Accounting & Finance

Invoice Processing Month-End Accruals

Marketing

Campaign Reports Lead Nurture Sequences
View all use cases

Developers

Docs Changelog Status

Learn

Blog Case Studies Events Partners
Pricing
Login Book Demo Start Free

Heap MCP Server
for AI Agents

Production-ready Heap MCP server with extensible actions — plus built-in authentication, security, and optimized execution.

Start Free Book Demo Read Docs →
Heap logo
Heap MCP Server
Built by StackOne StackOne

Coverage

6 Agent Actions

Create, read, update, and delete across Heap — and extend your agent's capabilities with custom actions.

MCP Actions → Create Actions →

Authentication

Agent Tool Authentication

Per-user OAuth in one call. Your Heap MCP server gets session-scoped tokens with zero credentials stored on your infra.

Agent Auth →

Security

Agent Protection

Every Heap 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 Heap call.

Tools Discovery →

What is the Heap MCP Server?

A Heap MCP server lets AI agents read and write Heap data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Heap 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 Heap MCP Tools and Actions

Every action from Heap's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.

Account Properties

  • Add Account Properties

    Set custom properties on a Heap account

Track Events

  • Track Event

    Send a single custom event to Heap

Bulk Track Events

  • Bulk Track Events

    Send up to 1000 custom events to Heap in a single request

Identify Users

  • Identify User

    Associate a Heap user_id with a known identity

User Properties

  • Add User Properties

    Set custom properties on a Heap user

Bulk Add User Properties

  • Bulk Add User Properties

    Set custom properties on multiple Heap users in a single request

Set Up Your Heap MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to Heap in under 10 lines of code.

MCP Clients

Agent Frameworks

Claude Desktop
{
  "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 Data & Analytics MCP Servers

Tableau

114+ actions

SurveyMonkey

104+ actions

Microsoft Excel

101+ actions

Qlik

100+ actions

Snowflake

80+ actions

PostHog

63+ actions

Amplitude

53+ actions

All Data & Analytics MCP Servers →

Heap 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

Heap MCP Server FAQ

Heap MCP server vs direct API integration — what's the difference?
A Heap MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Heap. A Heap 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 Heap at runtime. StackOne provides both.
How does Heap authentication work for AI agents?
Heap 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 Heap account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.
Are Heap MCP tools vulnerable to prompt injection?
Yes — Heap 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 Heap agent and how do I avoid it?
Context bloat happens when Heap tool schemas and API responses eat your Heap agent's memory, preventing it from reasoning effectively. A single Heap 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 Heap agent can access?
Yes — you can limit which actions your Heap 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 Heap MCP server?
Yes — you can create custom agent actions for your Heap MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Heap's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Heap MCP server?
Skip a Heap MCP server if your integration is purely software-to-software — direct Heap 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 Heap actions at runtime.
What AI frameworks and AI clients does the StackOne Heap MCP server support?
The StackOne Heap 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.

Start Free Book Demo