Editing Model Context Protocol

{{Infobox protocol
| name            = Model Context Protocol
| logo            = 
| developer       = [[Anthropic]]
| status          = Stable
| first_published = November 2024
| latest_version  = 
| transport       = [[wp:HTTP|HTTP]], stdio
| encoding        = [[wp:JSON-RPC|JSON-RPC 2.0]]
| license         = [[wp:MIT License|MIT]]
| website         = https://modelcontextprotocol.io
| spec_url        = https://spec.modelcontextprotocol.io
| repository      = https://github.com/modelcontextprotocol
}}

{{Main article|[[wp:Model_Context_Protocol]]}}

The '''Model Context Protocol''' ('''MCP''') is an [[wp:Open standard|open standard]] developed by [[Anthropic]] that provides a standardized way for [[wp:Large language model|large language models]] to connect with external tools, data sources, and APIs. Often described as the "USB-C port for AI," MCP enables AI applications to access real-time information and perform actions beyond their training data.

MCP was created by David Soria Parra and Justin Spahr-Summers at Anthropic and deliberately reuses message-flow concepts from the [[wp:Language Server Protocol|Language Server Protocol]] (LSP). Following its release, MCP was adopted by major AI providers including [[wp:OpenAI|OpenAI]] (March 2025) and [[wp:Google DeepMind|Google DeepMind]] (April 2025).

== Overview ==

MCP addresses a fundamental challenge in AI application development: integrating language models with external systems. Before MCP, developers needed to create custom integrations for each tool and data source, resulting in fragmented and difficult-to-maintain codebases.

=== Design philosophy ===

MCP follows several key principles:

* '''Vendor-agnostic''' – Works with any LLM provider, not just Anthropic
* '''Standardized interfaces''' – Consistent patterns for tool definition and invocation
* '''Security-focused''' – Built-in access control and audit capabilities
* '''Human-in-the-loop''' – Support for requiring human confirmation of actions

== Architecture ==

MCP uses a client-server model with three main components:

=== MCP Host ===

The host contains orchestration logic and manages connections between clients and servers. It can host multiple clients simultaneously.

=== MCP Client ===

Clients convert requests into the structured MCP format. Each client maintains a one-to-one relationship with an MCP server and handles session management, response parsing, and error handling.

=== MCP Server ===

Servers expose tools, data sources, and APIs to clients. They are typically implemented as standalone applications or services that provide access to specific capabilities.

== Technical specification ==

=== Transport layer ===

MCP supports two transport mechanisms:

* '''stdio''' – Standard input/output for lightweight, synchronous messaging
* '''SSE over HTTP''' – [[wp:Server-sent events|Server-Sent Events]] for asynchronous, event-driven communication

=== Message format ===

All messages use [[wp:JSON-RPC|JSON-RPC 2.0]] format:

{{Code example
| language = json
| caption  = Example tool call
| code     = {
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_weather",
    "arguments": {
      "location": "Berlin"
    }
  }
}
}}

=== Core primitives ===

MCP defines four core primitives:

{| class="wikitable"
|-
! Primitive !! Description
|-
| '''Resources''' || Data sources and files accessible to the model
|-
| '''Tools''' || Functions the model can invoke
|-
| '''Prompts''' || Pre-defined prompt templates
|-
| '''Sampling''' || Model inference requests
|}

== Adoption ==

Since its launch in November 2024, MCP has seen rapid adoption:

* Integrated into [[wp:Visual Studio Code|Visual Studio Code]] via GitHub Copilot
* Supported by [[wp:Amazon Web Services|AWS]] for agentic AI development
* Hundreds of community-developed MCP servers available

== Comparison with other protocols ==

MCP focuses on tool integration ("vertical" connections), while protocols like [[Agent-to-Agent Protocol|A2A]] handle agent-to-agent communication ("horizontal" connections). The two are complementary rather than competing standards.

== See also ==

* [[Agent-to-Agent Protocol]]
* [[Agent Communication Protocol]]
* [[Common Text-based Response Protocol]]
* [[Tool Calling]]

== References ==

{{Reflist}}

== External links ==

* [https://modelcontextprotocol.io Official website]
* [https://spec.modelcontextprotocol.io Protocol specification]
* [https://github.com/modelcontextprotocol GitHub organization]

[[Category:Communication Protocols]]
[[Category:Tool Use]]
[[Category:Anthropic Specifications]]