Glossary
What is the Model Context Protocol (MCP)?
The Model Context Protocol (MCP) is an open standard for connecting AI assistants to external tools and data sources. It defines how an AI client discovers and calls tools exposed by an MCP server, in a consistent, model-agnostic way.
What problem MCP solves
Before MCP, every AI app wired up tools in its own bespoke way. MCP standardizes the contract between AI clients and tool providers, so a tool built once works with any MCP-compatible assistant.
Clients and servers
An MCP client (the AI app or agent) connects to one or more MCP servers. Each server advertises tools with typed inputs and outputs; the client calls them on the model's behalf and feeds results back into the conversation.
MCP and Modiva
Modiva speaks MCP: its hosted server exposes social posting, scheduling, analytics and comment tools so any MCP client can manage social media through one secure connection.
FAQ
Is MCP open source?
Yes — MCP is an open standard, so any client or server can implement it without vendor lock-in.
Which AI clients support MCP?
MCP-compatible clients include Claude and Cursor, among a growing list; any of them can connect to Modiva's MCP server.