You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+40-17Lines changed: 40 additions & 17 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -10,23 +10,42 @@ Countly is an open-source, enterprise-grade product analytics platform. It helps
10
10
11
11
The Model Context Protocol (MCP) is an open protocol that enables seamless integration between AI applications and external data sources. This server implements MCP to allow AI assistants like Claude to interact with your Countly analytics data naturally through conversation.
12
12
13
+
## Requirements
14
+
15
+
### Server Requirements
16
+
-**Node.js 18+** (for local installation) OR **Docker** (recommended)
17
+
-**Countly Server**: Access to a Countly instance (cloud or self-hosted)
18
+
-**Auth Token**: Valid Countly authentication token with appropriate permissions
- Claude Desktop (recent versions supporting 2025-03-26 spec)
25
+
- Any MCP client implementing the Streamable HTTP transport protocol
26
+
27
+
> ⚠️ **Note**: For SSE type this server uses `StreamableHTTPServerTransport` which implements the modern MCP specification (2025-03-26). Older MCP clients that only support the legacy SSE protocol (2024-11-05) are not compatible. Please ensure your MCP client is up-to-date.
**Note**: The client can pass authentication via `metadata.countlyAuthToken`. The server will use this token to authenticate with your Countly instance.
71
+
**Note**: The VS Code MCP extension passes credentials via HTTP headers (`X-Countly-Server-Url` and `X-Countly-Auth-Token`). This allows multiple users to connect to the same Docker instance with their own credentials.
0 commit comments