Skip to main content
The Navattic MCP server gives AI coding agents — such as Claude Desktop, Cursor, VS Code Copilot, and Windsurf — structured access to your workspace. Agents can read analytics, browse and build demos, and query personalization data, all scoped to your workspace through a Personal Access Token.
The MCP server requires the MCP Server and Copilot features to be enabled for your workspace. Contact support@navattic.com if you’d like access.

​
How it works

You create a Personal Access Token in your workspace settings and provide it to your AI agent’s MCP configuration. The agent connects to https://app.navattic.com/api/mcp and discovers only the tools it has permission to use based on the token’s scopes and your workspace role. All operations are scoped to your workspace — agents cannot access data from other workspaces, even with a valid resource ID from another workspace.

​
Step 1: Create a Personal Access Token

1

Go to Access Tokens settings

Navigate to Settings > Access Tokens in your Navattic workspace.
2

Create a new token

Click Create token. Enter a name for the token (for example, “Claude Desktop” or “Cursor agent”).
3

Select scopes

Choose the scopes your agent needs. Each scope grants access to a specific set of tools:
ScopeWhat it allowsRequired role
AnalyticsView visitor summaries and engagement dataViewer or above
Demo BrowsingBrowse projects, flows, and share linksViewer or above
Demo BuildingCreate flows, edit steps, configure CTAsBuilder or above
Demo ManagementRename and organize projects; create share linksBuilder or above
Demo PublishingDeploy and archive projectsBuilder or above
PersonalizationView custom properties and visitor activityViewer or above
Start with Analytics and Demo Browsing — these cover read-only operations. Add write scopes only if your agent needs to create or modify demos.
4

Set an expiration

Choose a token lifetime: 7, 30, 60, 90, or 180 days. Tokens expire automatically; you’ll need to create a new token when one expires.
5

Copy the token

After creating the token, copy it immediately. You won’t be able to see it again.
Store your token securely. Anyone with the token can access your workspace within the granted scopes.

​
Step 2: Configure your MCP client

After copying your token, Navattic shows setup instructions for each supported agent. Add the configuration to your agent’s settings file:
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS):
{
  "mcpServers": {
    "navattic": {
      "url": "https://app.navattic.com/api/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_TOKEN"
      }
    }
  }
}
Restart Claude Desktop after saving.
Replace YOUR_TOKEN with the token you copied in Step 1.

​
Available tools

Once connected, your agent can see and call tools based on its token’s scopes. Tools are only visible to the agent if the token has the corresponding scope — the agent won’t see tools it can’t use.
ToolDescriptionScope
get_visitor_summaryView engagement metrics and visitor data for a projectAnalytics
list_projectsList all projects in the workspaceDemo Browsing
get_projectGet details, flows, and share links for a specific projectDemo Browsing
create_flowCreate a new flow within a projectDemo Building
rename_projectRename a projectDemo Management
archive_projectArchive a project (affects live demo URLs)Demo Publishing
list_custom_propertiesView custom properties configured for personalizationPersonalization
Your agent also has access to two workspace resources regardless of scopes:
  • Workspace overview — current project count, member count, and plan type
  • Navattic concepts — a reference guide to the Navattic data model (projects, flows, steps, share links)

​
Use cases

Ask your AI agent to summarize visitor engagement for a specific project. For example: “Which demos had the most drop-off last week?” or “Summarize visitor activity for our pricing demo.” The agent calls get_visitor_summary and presents the results inline in your editor.
Use your agent to create new flows within an existing project. Describe the steps you want in natural language and let the agent structure and create them via create_flow. This is useful when building many similar demos or automating demo creation as part of a deployment workflow.
Ask the agent to list all projects and find specific demos by name or description. The list_projects and get_project tools give the agent access to your full workspace library, including flow structure and share links.
Use the agent to rename or archive projects as part of a release workflow. For example, archive old version demos automatically when a new version is deployed.

​
Managing tokens

You can view all active tokens from Settings > Access Tokens. From there you can:
  • See each token’s name, scopes, creation date, and expiration
  • Revoke a token at any time — revocation takes effect immediately
When a token expires or is revoked, any agent using it will receive authentication errors until you update its configuration with a new token.

​
Frequently asked questions

Yes. Create a separate token for each agent or environment, and name them to make revocation easier. For example, “Claude Desktop - production” and “Cursor - local dev”.
Revoke the token immediately from Settings > Access Tokens. Then create a new token and update your agent configuration. The revoked token stops working as soon as you revoke it.
No. The scope picker automatically disables write scopes (Demo Building, Demo Management, Demo Publishing) for users with Viewer-only roles.
The agent can only access data within the scopes you selected when creating the token. All data is also restricted to your workspace — the agent cannot access data from other workspaces.