Definition
Model Context ProtocolMCP
An open standard for connecting AI applications to tools and data through reusable servers, instead of custom integrations per app.
The Model Context Protocol, introduced by Anthropic in late 2024 and since adopted widely, defines how an AI application (the client) discovers and uses capabilities exposed by MCP servers: tools it can call, resources it can read and prompt templates.
Exposing a system once as an MCP server lets any compatible agent or assistant use it, which reduces duplicated integration work and keeps permissions and logging in one place. Security still has to be designed: least-privilege scopes, authentication for remote servers, human approval for consequential actions and treating tool output as untrusted.
Related services