MCP & Tool Protocols
Model Context Protocol
MCP
An open protocol for connecting AI applications to external tools, data sources, and services in a standardized way.
Example
An assistant uses one standard protocol to discover and call tools from different providers.
Why it matters
It reduces repeated connection work by giving tools and applications shared communication rules.
You'll hear it
“This connection follows the same standard as our other AI tools.”
Can you control it?
Set by the team
The people building or running the AI choose this setup. An everyday user generally needs their help to change how this part works.
Common questions
- Does MCP decide which tools a model may use?
- No. The surrounding application, services and user permissions determine which actions are allowed.
- Does an MCP connection make a source trustworthy?
- No. A standard connection does not verify the source's claims or make its instructions trustworthy.
- What should teams review before enabling MCP?
- Check who provides the connection, what it can access or change, and how to disable it.