Your AI SaaS business, ready by this week!
Try demoYour AI SaaS business, ready by this week!
Try demoMCP (Model Context Protocol) is an open standard that lets an AI model connect to outside tools and data sources through a common interface, so one connector works with any app that supports the protocol.
Before MCP, every AI app had to build its own integration for each service. MCP splits the job in two: a service publishes an MCP server that describes its tools, and any MCP client, such as a chat app, can discover and call those tools.
A remote MCP server usually sits behind OAuth, so each user signs in to their own account and the AI only sees what that user is allowed to see.
For an AI platform, MCP turns a chat into an assistant that can act: look up a ticket, query a spreadsheet or create a task, without custom code for each service.
Aikeedo is an MCP client. Users connect remote MCP servers with OAuth and use their tools from chat, and the Connectors add-on adds a catalogue of ready-made connectors.
Discover more terms connected to this one
Function calling, or tool use, lets an AI model ask the app to run a tool, such as a web search, a calculator or an API call, and then use the result in its answer.
An AI agent is an AI system that works toward a goal in several steps, deciding which tools to use, acting, checking the result and continuing, rather than giving a single reply.
OAuth is the standard that lets a user grant an app limited access to an account on another service without sharing their password, as in "Sign in with Google" or connecting an MCP server.