Skip to main content Announcing Tool Policies: AI agent permissions down to the field Read the announcement
StackOne
Connectors
Connect

Connect to everything your agents need, without writing the infrastructure to get there.

Secure

Enterprise-grade controls to ensure your agent always meets security & compliance standards.

Optimize

Maximise agent efficiency – faster responses, increased accuracy, fewer tokens used.

For SaaS products Embedded AI agent integrations Give your product's agent every system your customers use.
Pricing
Login
Book Demo Start Free
StackOne
Connectors
Connect

Connect to everything your agents need, without writing the infrastructure to get there.

Secure

Enterprise-grade controls to ensure your agent always meets security & compliance standards.

Optimize

Maximise agent efficiency – faster responses, increased accuracy, fewer tokens used.

Pricing
Book Demo Start Free
Live 13 Actions

OpenReplay MCP Server
for AI Agents

Connect your AI agent to StackOne's OpenReplay MCP server and give it ready-to-use MCP tools out of the box. Auth, tool execution, and security all managed.

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

Coverage

13 Agent Actions

Agents can read, write, delete and run operations in OpenReplay. Extend your agent's capabilities with custom actions.

MCP Actions → Build Actions →

Authentication

Agent Tool Authentication

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

Agent Auth →

Security

Agent Protection

Every OpenReplay tool response scanned for prompt injection in milliseconds, with 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 OpenReplay call.

Tools Discovery →

What is the OpenReplay MCP Server?

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

Every StackOne action for OpenReplay, ready for your agent. Read, write, delete and run operations, scoped to exactly what you need.

Live Sessions

  • Retrieve Live Sessions

    Retrieve the sessions currently live in a project, optionally for one user (Enterprise Edition).

  • Search Live Sessions

    Search the live sessions of a project with filters, sorting and paging (Enterprise Edition).

Events

  • Retrieve Events

    Retrieve the events captured during a session, paged and optionally filtered.

All Jobs

  • List All Jobs

    List the data jobs of a project, such as user data deletion jobs.

Job Details

  • Get Job Details

    Get the status and details of one job.

Cancel Jobs

  • Cancel Job

    Cancel a job that has not finished yet.

Projects

  • Create Project

    Create a new project in the current OpenReplay tenant.

  • List Projects

    List all projects in the current OpenReplay tenant.

  • Get Project

    Get a single project by its project key.

User Sessions

  • Retrieve User Sessions

    Retrieve the recorded sessions of one user within a time window.

Users

  • Search Users

    Search the identified users of a project with a free-text query, filters and a time window.

  • Get User

    Get the profile of one identified user in a project.

  • Delete User

    Schedule deletion of a user's data from a project.

Set Up Your OpenReplay MCP Server in Minutes

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

MCP Clients

Claude Desktop setup guide
Claude Code setup guide
Cursor setup guide
Goose setup guide

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>"
      ]
    }
  }
}

Platform Resources

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 Hundreds of Connector Builds Taught Us

MCP wraps APIs, it doesn't replace them. After building hundreds of connectors that serve both, here's when each approach wins.

14 min read

OpenReplay MCP Server FAQ

Does StackOne have a OpenReplay MCP server?
Yes. StackOne offers a hosted OpenReplay MCP server, 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.
OpenReplay MCP server vs direct API integration: what's the difference?
A OpenReplay MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software work, where backend code calls OpenReplay. A OpenReplay MCP server is for AI agents that discover and call OpenReplay at runtime, such as MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI. StackOne provides both.
How does OpenReplay authentication work for AI agents?
OpenReplay authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK to get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own OpenReplay account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.
Are OpenReplay MCP tools vulnerable to prompt injection?
Yes. OpenReplay MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content, such as 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. It runs regex patterns in ~1ms, then a MiniLM classifier in ~4ms. Accuracy is 88.7%, and it runs entirely on CPU.
What is the context bloat of a OpenReplay agent and how do I avoid it?
Context bloat happens when OpenReplay tool schemas and API responses eat your OpenReplay agent's memory, preventing it from reasoning effectively. A single OpenReplay query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery reduces it by loading only the tools relevant to each query.
Can I limit which actions my OpenReplay agent can access?
Yes. You can limit which actions your OpenReplay 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 OpenReplay MCP server?
Yes. You can create custom agent actions for your OpenReplay MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research OpenReplay's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a OpenReplay MCP server?
Skip a OpenReplay MCP server if your integration is purely software-to-software, because direct OpenReplay 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 OpenReplay actions at runtime.
What AI frameworks and AI clients does the StackOne OpenReplay MCP server support?
The StackOne OpenReplay 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