MCP (Model Context Protocol) — Model Context Protocol
What is MCP (Model Context Protocol)?
MCP (Model Context Protocol) is an open standard that lets an AI application connect to external tools, data sources, and services through one consistent interface, instead of every integration needing its own custom, one-off connector. An MCP server exposes a set of tools and resources in a standard format; any MCP-compatible AI client or agent can discover and call them the same way, regardless of which underlying model it runs on.
More detail
Before MCP, connecting an AI agent to a new tool or data source typically meant writing a bespoke integration for that specific combination of model and tool; MCP standardizes that connection so the same server works across compatible clients.
An MCP server can expose read-only resources (documents, records) alongside callable tools (actions like sending a message or updating a record), giving an agent a structured, discoverable way to interact with a system.
Frequently asked
- What problem does MCP actually solve?
- It replaces a web of bespoke, one-off integrations between specific AI models and specific tools with one standard protocol, so a tool built as an MCP server works with any MCP-compatible AI client without a custom connector for each combination.
- Is MCP tied to one specific AI model or vendor?
- No — it's an open, model-agnostic protocol, meaning an MCP server built once can be used by any compatible AI client or agent, regardless of which underlying language model that client happens to run.
See also
Build it on Orbit
Voice, messaging, email, video, and AI agents on one platform and one pay-as-you-go bill. Start free — no credit card required.