How do I connect Replay MCP?

Sign up for Conductor Deck, then add a Replay MCP step to a workflow on the visual canvas. The builder walks you through the connection it needs — an account authorization or the required keys — right inside the step. No separate setup or code.

Yes — Conductor Deck has a free tier you can build and run workflows on, with no credit card required. Paid plans raise the monthly run limits and add advanced features when you need them.

What's the difference between a trigger and an action?

A trigger is the event that starts a workflow — for example, a Stream Deck button press or an incoming event from a connected app. An action is a step the workflow performs once it runs. A workflow is one trigger followed by one or more actions.

Replay MCP + Stream Deck

model-context-protocol · developer-tools · server-monitoring · 0 triggers · 32 actions

Replay MCP lets agents inspect time-travel browser recordings, including console output, exceptions, network activity, source code, React state, performance profiles, screenshots, and execution points. Add Replay MCP to your Stream Deck workflows with guided setup for the connection details it needs.

Build a Replay MCP workflow — free See how it works

No code
Free tier
One Stream Deck press
Pairs with OBS & Elgato tools
OAuth & keys handled in-builder

Popular ways to use Replay MCP

Add Replay MCP to a workflow and pair it with a Stream Deck button to run it in one press — handy for model-context-protocol tasks. Combine it with OBS, your Elgato tools, or any other app you connect to build a routine that fits how you work.

Browse all templates

Triggers & actions

Steps your workflow can perform in Replay MCP.

Annotations

Inspect the annotations in a recording. Annotations are timestamped records attached by the runtime and integrations (e.g. Cypress, Playwright, React DevTools, network, localStorage). Call with no arguments to list all annotation kinds in the recording with their counts. Pass a 'kind' to return the annotation data for that kind (paginated, optionally filtered by text). For WebSocket traffic (DOMWebSocket annotations), use the WebSocketMessages tool instead.

Consolemessages

Show console API messages (console.log, console.warn, console.error, etc.). Note: console errors are distinct from runtime exceptions — use UncaughtException and ReactException for those. Start with mode 'summary' for an overview with message counts and the last errors/warnings. Use 'messages' to browse the full paginated list (filter by level, text, node_modules visibility). Use 'message-detail' with a point reference for full detail on a single message including stack trace. Call RecordingOverview first for broader context.

Describepoint

Describes the application state at a code execution point. Shows the containing function with executed/not-executed annotations, variable values, and timestamps. Use dependencyChain=true to trace the full causal chain back to the origin event. Get execution points from other tools (ConsoleMessages, ReactRenders, ReduxActions, Logpoint, etc.).

Evaluate

Evaluates an expression at a code execution point. Use for ad-hoc value inspection beyond what DescribePoint shows. Expressions must be synchronous and immediately inspectable. Do not use async functions or promises; replay cannot inspect their eventual results. Defaults to frame scope; use global scope explicitly when needed. String results are returned in full up to maxStringLength characters (default 100000); longer strings end with a truncation notice giving the stringOffset to read the next part. String results longer than about 8,000 characters are read by evaluating the expression a second time, so use a single, side-effect-free expression to get the full text.

Executiondelay

Computes execution delays for functions based on their source length and the delay before the first breakpoint in each function executes. Each breakpoint is attributed to the innermost function covering it, and each function's weight is computed as its source length minus the sum of its children's lengths.

Getpointcomponent

Gets the React component being rendered at a code execution point.

Getpointlink

Generates an app.replay.io link for users to inspect a given execution point.

Getstack

Gets the call stack at a code execution point. Use to understand execution context. Pair with DescribePoint for full state.

About Replay MCP

model-context-protocoldeveloper-toolsserver-monitoring

How to connect

Sign up for free

Create your Conductor Deck account: no credit card required.

Connect Replay MCP

Follow the setup prompts for Replay MCP. Conductor Deck handles the app authorization or required connection details inside the workflow builder.

Build a workflow

Add a Replay MCP action to your visual workflow canvas. Configure the options you need, then connect it to other steps.

Assign to Stream Deck

Sync your workflow to any Stream Deck button. Press once to trigger the entire sequence.

Frequently asked questions

How do I connect Replay MCP?: Sign up for Conductor Deck, then add a Replay MCP step to a workflow on the visual canvas. The builder walks you through the connection it needs — an account authorization or the required keys — right inside the step. No separate setup or code.
Is it free?: Yes — Conductor Deck has a free tier you can build and run workflows on, with no credit card required. Paid plans raise the monthly run limits and add advanced features when you need them.
What's the difference between a trigger and an action?: A trigger is the event that starts a workflow — for example, a Stream Deck button press or an incoming event from a connected app. An action is a step the workflow performs once it runs. A workflow is one trigger followed by one or more actions.

Automate Replay MCP with your Stream Deck

Get started free View pricing

Similar integrations