What is MCP?
MCP (Model Context Protocol) is an open standard that defines how AI models and agents discover and invoke external tools. It provides a unified interface for tool registration, invocation, and result handling, enabling any AI system to use any MCP-compatible tool without custom integration code.
The Model Context Protocol was introduced to solve the n×m integration problem: n AI systems each needing custom integrations with m tools. MCP defines a standard wire protocol (typically JSON-RPC over stdio or HTTP) with well-defined messages for tool discovery (`tools/list`), invocation (`tools/call`), and resource access.
An MCP server exposes a registry of tools. Each tool has a name, description, and JSON Schema-described input parameters. An MCP client (typically an AI agent or model) queries the server for available tools, selects the appropriate tool, calls it with structured input, and receives structured output.
quickhelp.dev exposes all registered tools over MCP at `/mcp` (HTTP transport) and via stdio for local use with Claude Desktop. The same tool registry powering the REST API and OpenAPI spec automatically populates the MCP tool list — adding a new tool makes it available across all four surfaces at once.
MCP is a key part of the agent-native design: tools built for MCP are discoverable by any AI system that speaks the protocol.