Maze MCP

Last updated: July 7, 2026

The Maze MCP connects your Maze account to AI apps like Claude, Cursor, Copilot, and ChatGPT. It allows you to search for studies, review responses and transcripts, and analyze research seamlessly in your workflow.

Once connected, you can ask questions about your research directly in the apps you already use — without logging into Maze or exporting anything.

MCP (Model Context Protocol) is an open standard that lets AI apps connect to external tools and data sources. Maze runs a remote MCP server that your AI app connects to over HTTPS. When you ask a question, your app sends the prompt to Maze's server, which returns the relevant data (transcripts, results, insights) for the app to use in its response.

Maze's MCP is currently in Beta. Please request access here.

What you can do with the Maze MCP

Read study details and transcripts

Pull up what a specific study covered, how it was set up, and what participants said, without opening Maze.

Go deeper on a specific study

  • "Walk me through the results of [study name]."

  • "Where did participants struggle in [study name]?"

  • "What were the most common drop-off points in [study name]?"

Surface patterns across studies

Instead of reading reports one at a time, ask your AI app to look across multiple studies and tell you what keeps coming up — useful for spotting recurring problems or confirming that a finding isn't a one-off.

  • "What themes keep coming up across our [topic] research?"

  • "Is [problem] showing up in more than one study?"

  • "How have reactions to [feature] changed between [study A] and [study B]?"

Pain points analysis and quotes gathering

Extract the top friction points from a study and surface direct participant quotes. Good for quickly building the "what users said" evidence base for a decision or document.

  • “What are the top pain points from this study?”

  • “How [confident/comfortable/etc] are users using our [product X], considering the unmoderated study we ran recently about [product X]?”

  • “Based on the transcripts, what are the key quotes/highlights from the users?”

Search across your research

Ask questions like "What did participants say about the checkout flow?" and get findings pulled from across your studies, with the source and study context attached.

Check what research already exists

Before starting a new study, ask what's already been run on a topic to avoid duplicating work.

  • "What research exists on [topic] in my [workspace name] workspace?"

  • "Has anything been run on [feature] in the last six months?"

  • "Are there any themes tagged [topic] across our studies?"

Study and action recommendations and guidance

Get the "so what" from a study: what to improve next time, what opportunities to pursue, and what follow-up research makes sense.

  • “What could I do better next time if I were to re-run the study again in the future?”

  • “What are the top key opportunities from this study?”

  • “For this study, what are the recommended next steps/further research projects we should do next?”

Work in the apps you already use

Everything above works inside Claude, Cursor, ChatGPT, and any MCP-compatible app. Your existing Maze permissions apply; you only see what you already have access to.

Set up Maze MCP

Claude (Desktop App and claude.ai)

For Pro and Max plans:

  1. Go to Settings → Customize → Connectors (or directly to customize from the sidebar)

  2. Click "+" (top right)

  3. Then "Add custom connector"

  4. Add the URL: https://connect.maze.co/mcp

  5. More info here: https://support.claude.com/en/articles/11175166-get-started-with-custom-connectors-using-remote-mcp#h_3d1a65aded

For Team and Enterprise plans:

Preliminary steps for owners: Before members of Team and Enterprise plans can configure custom connectors, an Owner or Primary Owner needs to follow these initial steps to add a custom connector to your organization:

  1. Navigate to Organization settings > Connectors.

  2. Click the "Add" button.

  3. Hover over “Custom,” then select “Web.”

  4. Add Maze’s connector URL: https://connect.maze.co/mcp

  5. Finish configuring your connector by clicking "Add."

Steps for members after connector is configured:

  1. Navigate to Customize > Connectors

  2. Find the Maze connector your Owner added in the list (it will have a "Custom" label).

  3. Click "Connect" to authenticate and start using the connector with Claude.

More info here: https://support.claude.com/en/articles/11175166-get-started-with-custom-connectors-using-remote-mcp#h_3d1a65aded

ChatGPT

  1. Go to your ChatGPT account

  2. Click on Apps in the left sidebar

  3. Search for Maze and select it

  4. Click Connect

Cursor

  1. Open Cursor and go to Settings → Tools & MCPs

  2. Click Add Custom MCP

  3. Paste the following config under mcpServers:

{
  "mcpServers": {
    "maze-connect": {
      "url": "https://connect.maze.co/mcp"
    }
  }
}

  1. Save, then return to Tools & MCPs and click Connect on the Maze entry

GitHub Copilot (VS Code)

Option A — Command Palette:

  1. Open the Command Palette (⇧⌘P on Mac / Ctrl+Shift+P on Windows/Linux) and run MCP: Add Server

  2. Choose HTTP (Streamable)

  3. Enter the server URL: https://connect.maze.co/mcp

  4. Name it maze-connect and choose Global (all workspaces) or Workspace

Option B — Edit config directly:

Run MCP: Open User Configuration for a global setup, or create .vscode/mcp.json in your workspace, and add:

json
 {
"servers":  {
  "maze-connect": {
    "type": "http",
    "url": "https://connect.maze.co/mcp"
    }
   }
  }

Then:

  1. Click Start on the CodeLens above the server entry in mcp.json

  2. Click Auth to complete the OAuth flow in your browser

  3. In the Chat view, switch the mode picker to Agent — Maze tools appear under Configure Tools in the chat input (or type # to reference them)

Verify it works: Run "Which Maze teams am I in?" — Copilot should respond with your team list.

Microsoft Copilot

To enable Maze MCP inside Copilot and other Microsoft channels (like Microsoft Teams) you need to create a new agent with a custom tool connector that points to our MCP:

  1. Go to https://copilotstudio.microsoft.com/ and sign in

  2. Go to the Agents tab and Click on Create blank agent

  3. Enter the name of the agent; we recommend Maze

  4. On the overview page you can setup a user facing description, choose the model you want to use for the agent and enter custom instructions to further customize the agent. We recommend also disabling web search since Maze MCP doesn’t need it

  5. Go to the Tools section and click Add a tool

  6. Select the Model Context Protocol card and enter:

    1. Server name - Maze Connect

    2. Server description - Connect Maze to look up research studies, review session results, and surface user insights without leaving the workflow. Find studies by topic even when the study name is unknown, go through participant responses and task metrics, retrieve highlights and themes from moderated and unmoderated sessions, and pull recordings or transcripts for deeper analysis. This is useful for pulling evidence for a product decision, synthesizing research before a design review, or catching up on studies that have not been reviewed yet.

    3. Server URL - https://connect.maze.co/mcp

    4. Authentication - Select OAuth 2.0 and type Dynamic discovery

    5. Click create

    6. Once created click on the Connection and create a new connection - you will be prompted for your Maze Account and authorizing access for the MCP

    7. Once the connection is set click Add and configure

  1. If everything set up correctly, you should see the tool and resources list populated

    1. If the agent was still provisioning you might need to refresh the tool list and resources list

  2. Use the right chat box to test your agent (try: “What maze teams am I apart of” or some other prompt from the help article)

    1. You will be asked to Open connection manager to setup the connection for the user. This is because the Agent uses the users Maze permissions instead of a service level account. Once done hit retry and check the MCP returns a result

  3. On the channels tab choose which channel you want to provision your agent for

  4. Hit publish to publish your agent

    1. Depending on your organization settings, you might need an admin to approve the agent to appear in the correct channels

Other AI apps

Claude Code (CLI)

  1. Run the following in your terminal:

claude mcp add --transport http maze-connect https://connect.maze.co/mcp

  1. Open a Claude session

  2. Run /mcp and select maze-connect (it will indicate authentication is needed)

  3. Click Authenticate and follow the auth flow in your browser

Codex

  1. Open the Codex app and run:

codex mcp add maze-connect --url https://connect.maze.co/mcp

  1. If not automatically prompted to log in, run:

codex mcp login maze-connect

  1. Fully close the Codex app (don't just minimize it) and reopen it — Maze MCP will now be available

Data and privacy

Who can connect

Maze MCP is available on Enterprise plans. Any user on an Enterprise team can connect their account to an MCP-compatible AI app — connecting grants access to your own account only and doesn't give other users access to your research.

If you're on a team with multiple plan types, you'll only be able to access studies and data from your Enterprise-plan team(s) through MCP.

Your organization admin may need to enable third-party connectors before you can connect. If you don't see the option, ask your admin to check your organization's connector settings. Authorization uses OAuth 2.1, an industry-standard security protocol.

What happens when you ask a question

Your AI app sends your prompt to Maze's MCP server, which returns the relevant research data — transcripts, results, metadata — for the app to use in its response. Access is read-only: your AI app can query your research, but can't create or modify anything in Maze.

What your AI app can access

Your existing Maze workspace permissions apply. If you can't open a study in Maze, your AI app can't read it either.

Your AI app can't:

  • Create, edit, or delete anything in Maze (read-only access)

  • Access studies or data outside your workspace permissions

  • Read billing information or account credentials

Team data boundaries

Your existing Maze workspace permissions apply throughout.

Maze MCP respects your team’s existing access controls. This means that, if your team has limited access workspaces, those boundaries apply to MCP queries the same way they apply in the Maze app.

What Maze stores

Maze doesn't store your prompts or conversation history. What's stored in Maze stays the same as always: your studies, results, and research data.

Revoking access

Disconnect at any time from within your AI app's settings. Revoking access doesn't delete any research data; it only removes the app's permission to read it.

Still need help?

If you have any questions or concerns, please let our Support team know — we'll be happy to help!