← Knowledge Base

Model Context Protocol (MCP)

An open protocol by Anthropic that standardizes how AI applications connect to external tools and data sources.

Definition

What Is Model Context Protocol (MCP)?

Model Context Protocol (MCP) is an open standard developed by Anthropic that defines how AI applications (clients) connect to external tools and data sources (servers) through a structured, discoverable interface. MCP provides a JSON-RPC-based protocol where servers declare their capabilities — tools (executable functions), resources (readable data), and prompts (reusable templates) — and clients discover and invoke them at runtime. The protocol supports multiple transport mechanisms including stdio (for local tools) and HTTP with server-sent events (for remote services).

Origin

Where It Came From

MCP was introduced by Anthropic in late 2024 as a response to the fragmented landscape of AI tool integrations. Before MCP, every AI application that needed to interact with external tools built custom integrations — creating an N-to-M problem where N AI clients each needed custom connectors for M tools. MCP solves this by defining a common protocol: build an MCP server for your tool once, and any MCP-compatible client can use it. The protocol was open-sourced with reference implementations in TypeScript and Python, and adopted by tools including Claude Desktop, Claude Code, Cursor, and others.

Applications

Use Cases

  • Building tool servers that expose database access, API wrappers, or file operations to any MCP-compatible AI client
  • Creating development environment integrations that give AI assistants access to git, build tools, and test runners
  • Implementing governance tools that expose constraint checking, pattern validation, and knowledge search as MCP tools
  • Connecting AI agents to enterprise systems (CRM, ticketing, monitoring) through standardized MCP interfaces

Ecosystem

Related Technologies

  • JSON-RPC 2.0 (transport protocol)
  • JSON Schema (tool input/output definitions)
  • Server-Sent Events (SSE for streaming)
  • Claude Desktop, Claude Code, Cursor (MCP clients)
  • TypeScript SDK, Python SDK (reference implementations)

References

Further Reading

Related

Related Topics

Model Context Protocol (MCP)

An open standard for connecting AI models to external tools and data sources through a unified, structured interface.

AI Workflow Orchestration

Coordinating multi-step AI workflows — from single-agent task execution to multi-agent fan-out with parallel tool calls.

AI Agent Observability

Monitoring, tracing, and understanding AI agent behavior in production — from token usage to decision quality.

AI Production Systems

Engineering practices for deploying and operating AI systems in production — beyond prototypes and demos.