OasisGet started

Enter your Oasis

Back to Glossary

MCPs and AI Connectors

Model Context Protocol, agent-to-tool connections, integrations, and the plumbing that links agents to data and systems.

12 questions

Core concepts

How do you give an AI agent tools? (MCP vs direct API)You register each tool as a name, description, and argument schema, then run the call the model requests and return the result.Read the full answer
What is AI agent integration?AI agent integration is the set of permissions that let an agent read from and act inside the apps you already use.Read the full answer
What is an MCP connector? (And why it's also called a server)An MCP connector is a single tool an agent can use, like Gmail or Slack, added by approving what that tool may do.Read the full answer
What is an MCP gateway? (And when your org needs one)An MCP gateway is one control point between an organization's AI agents and its MCP servers, governing access, credentials and audit logging.Read the full answer
What is an MCP registry? (And what it does not check)An MCP registry is a public list of MCP servers, showing what each connector does, who publishes it, and where to get it.Read the full answer
What is an MCP server?An MCP server is a program that exposes tools, resources and prompts to LLM clients over the Model Context Protocol.Read the full answer
What is MCP security?MCP security is the set of controls that stop an MCP server's tools, text and credentials from producing unauthorized actions.Read the full answer
What is the A2A protocol?A2A is an open protocol that lets independent AI agents discover each other and delegate tasks to each other over HTTP.Read the full answer
What is the Model Context Protocol (MCP)?MCP is an open JSON-RPC standard that lets any AI application discover and call tools, data and prompts exposed by external services.Read the full answer

Comparisons and decisions