{"article":{"id":26998738930972,"url":"https://countly.zendesk.com/api/v2/help_center/en-us/articles/26998738930972.json","html_url":"https://support.countly.com/hc/en-us/articles/26998738930972-Connecting-Countly-to-your-AI-Assistant","author_id":11350148999193,"comments_disabled":true,"draft":false,"promoted":true,"position":0,"vote_sum":0,"vote_count":0,"section_id":360007309132,"created_at":"2026-04-23T17:39:19Z","updated_at":"2026-08-25T16:24:14Z","name":"Connecting Countly to your AI Assistant","title":"Connecting Countly to your AI Assistant","source_locale":"en-us","locale":"en-us","outdated":false,"outdated_locales":[],"edited_at":"2026-08-25T16:24:14Z","user_segment_id":null,"permission_group_id":2891852,"content_tag_ids":[],"label_names":[],"body":"

You can use Countly with Claude Desktop or VS Code + GitHub Copilot so your AI assistant can work with real analytics, events, crashes, and dashboards.

Once connected, you can ask things like: 

To get more ideas on what you can do check here.

This article guides you to achieve this by setting up the Countly MCP Server.

Getting Started

\n
\n

\n Privacy is at our core. For that reason, if you’re connecting\n an AI assistant to your Countly data,\n we recommend using a self-hosted Countly instance alongside a self-hosted\n or on-premise LLM. If you use a cloud-based AI assistant like Claude Desktop\n or GitHub Copilot, be aware that your queries will pass through that provider’s\n infrastructure and ensure this aligns with your data policy.\n

\n

You'll need the following to get started:

If you know what you want to do, you can limit the token to a specific endpoint only (Events, Crashes etc.)
If you set an expiration, you will need to create a new token later and update your configuration.

Self-hosted Countly Users

If you use self-hosted Countly, we suggest running MCP locally or inside your own infrastructure. This prevents you from sending your Countly URL and token to external services. 

Claude Desktop

Claude Desktop is the easiest way to get started. Follow the step-by-step guide below.

Step 1: Open the MCP configuration

Option A (recommended): 

In Claude Desktop, go to Settings -> Developer -> Local MCP Servers -> click Edit Config:

Option B (manual): open the following file: 

macOS: 

~/Library/Application Support/Claude/claude_desktop_config.json

Windows: 

%APPDATA%\\Claude\\claude_desktop_config.json

Step 2: Adding Countly MCP 

If your config is empty, paste the following: 

{\n \"mcpServers\": {\n   \"countly\": {\n     \"command\": \"npx\",\n     \"args\": [\"-y\", \"--prefer-online\", \"countly-mcp-server@latest\"],\n     \"env\": {\n       \"COUNTLY_SERVER_URL\": \"https://your-countly-url.com\",\n       \"COUNTLY_AUTH_TOKEN\": \"YOUR_TOKEN\"\n     }\n   }\n }\n}

If you already have other MCP Servers, just add Countly inside the existing mcpServers object. For example:

{\n \"mcpServers\": {\n   \"existing-server\": {\n     \"command\": \"...\"\n   },\n   \"countly\": {\n     \"command\": \"npx\",\n     \"args\": [\"-y\", \"--prefer-online\", \"countly-mcp-server@latest\"],\n     \"env\": {\n       \"COUNTLY_SERVER_URL\": \"https://your-countly-url.com\",\n       \"COUNTLY_AUTH_TOKEN\": \"YOUR_TOKEN\"\n     }\n   }\n }\n}

Replace the https://your-countly-url.com with your actual Countly URL, and YOUR_TOKEN with your Countly auth token and save the file

Step 3: Restart Claude Desktop

Important: Fully quit Claude (not just close the window), then re-open it.

Once reopened, you should see the Countly MCP server now listed, as shown in the screenshot below:

Step 4: Verify it works

Open a new (or existing) chat, click on the \"heavy\"heavy➕ (plus) icon, and you should see Countly tools listed, like in the screenshot below: 

You can now try asking questions like \"List my Countly apps\".  If you get a response, it means the Countly MCP Server was successfully set up!

VS Code + GitHub Copilot

Step 1: Open the MCP config file

Open VS Code and open the Command Palette, select Show and Run Commands:

Run: MCP: Open User Configuration, like in the example below: 

This will open the mcp.json file, where you can add the Countly config described in the next step.

Step 2: Add Countly config

{\n \"servers\": {\n   \"countly\": {\n     \"type\": \"stdio\",\n     \"command\": \"npx\",\n     \"args\": [\"-y\", \"--prefer-online\", \"countly-mcp-server@latest\"],\n     \"env\": {\n       \"COUNTLY_SERVER_URL\": \"https://your-countly-url.com\",\n       \"COUNTLY_AUTH_TOKEN\": \"YOUR_TOKEN\"\n     }\n   }\n }\n}

Step 3: Verify it works

Verify that the configuration was set completely. 

Run: MCP: Show Installed Servers from your Command Palette:

You should see \"Countly\" installed, like in the screenshot below:

Run: MCP: List Servers from your Command Palette to check the Countly server's status: 

If you see that the countly server is \"stopped\": 

Click on countly and \"Start Server\": 

Once started, in your VS Code's output console, you should see the logs similar to the following: 

2026-04-23 15:11:28.252 [info] Starting server countly\n2026-04-23 15:11:28.253 [info] Connection state: Starting\n2026-04-23 15:11:28.254 [info] Starting server from LocalProcess extension host\n2026-04-23 15:11:28.254 [info] Connection state: Starting\n2026-04-23 15:11:28.254 [info] Connection state: Running

Now that the Countly MCP server is running, you can try @countly list my apps on your GitHub Copilot chat inside VS Code: 

Advanced Configuration

By default, the MCP server exposes the tools available for your Countly instance and token permissions.

You can add extra restrictions to the MCP server configuration using COUNTLY_TOOLS_* environment variables.

This is useful when you want the AI assistant to: 

All additional restrictions you add must be placed under the env section of your MCP config file; this applies to both the Claude Desktop and the VSCode + GitHub Pilot options.

CRUD Permission Values

You can change the CRUD permissions the AI can perform. 

\n
\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
ValueMeaning
NoneDisable tools
RRead only
CR Create + Read
CRUCreate + Read + Update
CRUDCreate + Read + Update + Delete
\n

For example, you can add \"COUNTLY_TOOLS_ALL\": \"R\" to allow read-only access. 

You'll need to add this under the env section on the MCP's config file:

{\n\"servers\": {\n  \"countly\": {\n    \"type\": \"stdio\",\n    \"command\": \"npx\",\n    \"args\": [\"-y\", \"--prefer-online\", \"countly-mcp-server@latest\"],\n    \"env\": {\n      \"COUNTLY_SERVER_URL\": \"https://your-countly-url.com\",\n      \"COUNTLY_AUTH_TOKEN\": \"YOUR_TOKEN\",\n      \"COUNTLY_TOOLS_ALL\": \"R\"\n    }\n  }\n}\n}
\n
Apply One Rule to Everything
\n

To make all MCP tools read-only: \"COUNTLY_TOOLS_ALL\": \"R\", 
To disable all MCP tools by default: \"COUNTLY_TOOLS_ALL\": \"NONE\".
You can then enable only specific categories.

\n

Enable Selected Categories Only 

For example, you can allow analytics and events as read-only, but disable everything else:

\"COUNTLY_TOOLS_ALL\": \"NONE\",\n\"COUNTLY_TOOLS_ANALYTICS\": \"R\",\n\"COUNTLY_TOOLS_EVENTS\": \"R\",\n\"COUNTLY_TOOLS_APPS\": \"R\"

This is a good setup for users who only want to explore analytics.

Read-only Analytics Setup

This allows general read-only access while explicitly disabling more sensitive areas.

\"COUNTLY_TOOLS_ALL\": \"R\",\n\"COUNTLY_TOOLS_DATABASE\": \"NONE\",\n\"COUNTLY_TOOLS_DASHBOARD_USERS\": \"NONE\",\n\"COUNTLY_TOOLS_APP_USERS\": \"NONE\"

Allow Limited Write Actions

For example, you can allow your AI assistant to create and read notes, but not update or delete them: 

\"COUNTLY_TOOLS_ALL\": \"R\",\n\"COUNTLY_TOOLS_NOTES\": \"CR\"

Use this when you want AI to help document findings without modifying existing notes.

Allow Crash Workflow Actions

This keeps most tools read-only, while allowing crash-related create/read/update actions if supported by your Countly permissions. 

For example:

\"COUNTLY_TOOLS_ALL\": \"R\",\n\"COUNTLY_TOOLS_CRASHES\": \"CRU\"

Token Permissions Still Matter

It's important to note that MCP restrictions do not override Countly token permissions.

The final access is the more restrictive combination of:

    \n
  1. What your Countly token allows
    2. \n
  2. What MCP server configuration allows
    3. \n

For example: 

As a result, delete will still not work.

Troubleshooting

\n
\n
No connectors are showing in Claude Desktop
\n
\n

If you don't see any Countly tools available, try the following:

\n
    \n
  • Restart Claude fully
    • \n
  • Check the config JSON format
    • \n
  • Check the token
    • \n
\n
\n
\n
\n
Authentication Errors
\n
\n

If you're seeing authentication errors, it could be due to:

\n
    \n
  • Wrong token
    • \n
  • Expired token
    • \n
  • Wrong URL
    • \n
\n
\n
\n
\n
Server connects and works, but it's limited
\n
If the Countly MCP server is connecting and working but is limited, the token permissions may be too narrow. Check the auth token you created in the Token Manager and grant the required scopes.
\n
\n

Security Notes

What can you do with Countly MCP?

","user_segment_ids":[]}}