analytics
MCP server from zoho/analytics-mcp-server
claude mcp add --transport stdio zoho-analytics-mcp-server docker run -i zohoanalytics/mcp-server:latest \ --env ANALYTICS_ORG_ID="Your Zoho Analytics organization ID" \ --env ACCOUNTS_SERVER_URL="Your Zoho Analytics Accounts Domain URL (https://accounts.zoho.com)" \ --env ANALYTICS_CLIENT_ID="Your Zoho Analytics OAuth client ID" \ --env ANALYTICS_SERVER_URL="Your Zoho Analytics API base URL (https://analyticsapi.zoho.com)" \ --env ANALYTICS_MCP_DATA_DIR="Directory for storing temporary data files" \ --env ANALYTICS_CLIENT_SECRET="Your Zoho Analytics OAuth client secret" \ --env ANALYTICS_REFRESH_TOKEN="Your Zoho Analytics OAuth refresh token"
How to use
The Zoho Analytics MCP Server acts as a bridge between AI agents and Zoho Analytics by implementing the Model Context Protocol (MCP). It exposes tooling that lets agents query and analyze data from Zoho Analytics, such as listing workspaces, retrieving views, and executing data queries. Common capabilities include getting workspaces, getting views within a workspace, and performing query_data style operations to extract insights from stored analytics data. Deployers can run the server via Docker and configure OAuth credentials and endpoints as environment variables to enable secure access to Zoho Analytics APIs. Once running, MCP hosts or clients can connect to the server using the MCP protocol and start issuing data-aware prompts to retrieve structured analytics results and run analyses through the provided tools.
How to install
Prerequisites:
- Docker installed on the host system
- Zoho Analytics OAuth credentials (Client ID, Client Secret, Refresh Token) and Org ID
Install and run the server using Docker:
- Pull the pre-built Docker image (latest tag):
docker pull zohoanalytics/mcp-server:latest
- Create a .env file (or export environment variables) with required credentials:
# Example values; replace with your own
ANALYTICS_CLIENT_ID="<your-client-id>"
ANALYTICS_CLIENT_SECRET="<your-client-secret>"
ANALYTICS_REFRESH_TOKEN="<your-refresh-token>"
ANALYTICS_ORG_ID="<your-org-id>"
ANALYTICS_MCP_DATA_DIR="/path/to/data"
ACCOUNTS_SERVER_URL="https://accounts.zoho.com"
ANALYTICS_SERVER_URL="https://analyticsapi.zoho.com"
- Run the MCP server container with the environment variables:
docker run -d --name zohoanalytics-mcp \
-e ANALYTICS_CLIENT_ID="<your-client-id>" \
-e ANALYTICS_CLIENT_SECRET="<your-client-secret>" \
-e ANALYTICS_REFRESH_TOKEN="<your-refresh-token>" \
-e ANALYTICS_ORG_ID="<your-org-id>" \
-e ANALYTICS_MCP_DATA_DIR="/path/to/data" \
-e ACCOUNTS_SERVER_URL="https://accounts.zoho.com" \
-e ANALYTICS_SERVER_URL="https://analyticsapi.zoho.com" \
zohoanalytics/mcp-server:latest
- Verify the container is running:
docker ps | grep zohoanalytics-mcp
- Point your MCP host or client to the running server using the MCP protocol. The host can optionally override ports or network settings as needed.
Additional notes
Tips and caveats:
- Ensure your Zoho OAuth credentials have the necessary scopes (Zoho Analytics API) and that the refresh token remains valid.
- The ANALYTICS_MCP_DATA_DIR path should be accessible to the container for temporary data storage.
- If you encounter API rate limits or token lifecycle issues, review the token management flow and consider implementing token refresh handling in your hosting environment.
- The server exposes endpoints that support tools like get_workspaces, get_views, and query execution. Review your MCP host documentation for how these tools map to MCP actions.
- For remote hosting, consider setting STORAGE_BACKEND and related Redis variables if you need distributed storage across multiple instances.
Related MCP Servers
mcp-vegalite
MCP server from isaacwasserman/mcp-vegalite-server
github-chat
A Model Context Protocol (MCP) for analyzing and querying GitHub repositories using the GitHub Chat API.
nautex
MCP server for guiding Coding Agents via end-to-end requirements to implementation plan pipeline
pagerduty
PagerDuty's official local MCP (Model Context Protocol) server which provides tools to interact with your PagerDuty account directly from your MCP-enabled client.
futu-stock
mcp server for futuniuniu stock
mcp -boilerplate
Boilerplate using one of the 'better' ways to build MCP Servers. Written using FastMCP