What it does
The server provides customer churn prediction and retention analytics through the MCP protocol. The publisher's examples refer to three tools: predict_churn, batch_predict_churn and get_customer_risk. The publisher describes it as part of the MEOK AI Labs ecosystem of MCP servers and states that it is built with EU AI Act provisions in mind, citing Articles 9, 13, 15, 26 and 50. This entry does not verify those claims.
A team would reach for it when an AI assistant needs to score churn risk for a single customer, score many customers in one batch, or look up the risk profile of a named customer. The readme does not describe specific business use cases beyond these tools.
The server is installed as the Python package churn-predictor-ai-mcp and runs over stdio transport. It is added to an MCP client configuration, such as claude_desktop_config.json for Claude Desktop. Once configured, the assistant can call the tools on request. The publisher links to full documentation, an API reference and an EU AI Act compliance guide.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
io.github.CSOAI-ORG/churn-predictor-ai-mcp
Churn Predictor Ai MCP Server by MEOK AI Labs
v1.0.10As shown on registry.modelcontextprotocol.io when we last read it