What is the Model Context Protocol (MCP)?
The Model Context Protocol is an open standard that lets an AI assistant connect to external tools and data sources, so the assistant can read from and act in another system without that system building a custom integration for each assistant.
Also called: MCP, MCP server.
Before MCP, connecting an assistant to a product meant a bespoke integration per assistant. MCP replaces that with one interface: a product exposes an MCP server, and any compatible client can use it.
For the user this shows up as being able to do real work from inside the assistant they already have open. Rather than switching to another application, you ask, and the work happens in the underlying product.
Access is scoped by key, which matters when the underlying product holds several clients or brands. A key limited to one brand can only act within it, and revoking the key ends the access.
It is a plumbing standard rather than a feature, which is why the interesting question is never whether a product supports MCP but what it lets you actually do once connected.
Common questions.
Which assistants support MCP?
Claude and ChatGPT both do, as do a growing number of agent frameworks and developer tools. Because it is an open standard, any compatible client works.
What can you do with Depost AI’s MCP server?
Draft posts, pull analytics, manage the content calendar, and work the approval queue without leaving the assistant. Keys are scoped to a single brand or a whole workspace, and it is included on every plan, Solo included.
In the product
See also