Are MCP servers safe for MSP client data?

It depends on where the MCP server runs. A hosted one routes your data through someone else’s cloud. MSP Skills connectors run locally on your own machine with your own credentials, send nothing to outside servers, and return only query results to the AI - never a raw dump of client data. Every command is tiered read / write / destructive, and your own tenant scopes what the API key can reach. That design is what makes them safe.

Why “where it runs” is the whole question

An MCP server is a connector that lets your AI call a real system on your behalf. The safety question is almost entirely about location:

The two layers of control

  1. Command tiers. Reads run autonomously; writes require a --dry-run preview and your approval; destructive actions require a human. Each connector ships this policy in its governance.md.
  2. Server-side scoping. Issue the API key inside your own PSA or backup tenant and scope it there. The connector can never exceed what your tenant granted - this control does not depend on the agent behaving.

Read this next