Skip to main content

One doc tagged with "shadow servers"

View all tags

MCP data flow and least collection: when I connect an MCP server, which slice of my private context gets handed over, and who over-collects

In one sentence the MCP spec states plainly that "hosts must obtain explicit user consent before exposing user data to servers," and Anthropic's software directory policy goes further — software "must only collect data from the user's context that is necessary to perform their function" and "must not collect extraneous conversation data, even for logging purposes." Yet in practice a server is routinely granted far more scope than it needs (the entire home directory to serve one folder), credentials concentrate into a single high-value target across servers, and data detours through someone else's infra on a third-party-hosted server. Conclusion first: map which context fields each server actually receives, and whether those fields are what it needs, before you decide to connect it. Treating "only connect official servers" or "one consent prompt is enough" as the whole boundary is the most common operational false security at this layer.