# MCP security

MCP security covers the risks of connecting an AI agent to tools through the Model Context Protocol (MCP). The tool descriptions and results a server sends are untrusted text that the model may follow as instructions.

## How MCP works

MCP is an open standard for connecting AI applications to tools and data. A server offers tools, each with a name, a description and an input schema. The application shows the descriptions to the model, sends its calls to the server and returns the results.

## Risks

- **Tool poisoning.** A description is text the model reads and the user rarely sees. A malicious server can hide instructions in it, or change it after approval.
- **Injection through results.** A tool's result is untrusted text too: a web page or a ticket an attacker wrote can carry an [indirect prompt injection](/glossary/indirect-prompt-injection).
- **Broad permissions.** A server often holds a token for a whole mailbox or every repository, and one injected step can use all of it. See [excessive agency](/glossary/excessive-agency).

## Controls

- **Vet servers.** Install only ones you trust, pin versions and review tool descriptions when they change.
- **Least privilege.** Give each server a narrow token, read-only where possible, and connect only the servers the task needs.
- **Check calls and results.** [Check each call's arguments](/glossary/tool-call-guardrails) before it runs, and scan each result before the model reads it.

## With White Circle

[Control](/products/control) checks tool calls before they run and blocks injected instructions before they reach a tool.

