Kept on Wikipedia:Model Context Protocol
The Model Context Protocol (MCP) is an open-source framework introduced by Anthropic to standardize the way artificial intelligence (AI) models like large language models (LLMs) integrate and share data from diverse sources.[1] Similar to how USB-C standardizes connections between devices and peripherals, MCP provides a universal interface for AI models to seamlessly integrate and interact with external data sources and tools.[2]
Background
The protocol was announced in November 2024[3] as an open-source[4] standard for connecting AI assistants to systems where data lives, including content repositories, business tools, and development environments.[5] It addresses the challenge of information silos and legacy systems that constrain even the most sophisticated AI models.[5]
Features
MCP defines a set of specifications for:
- Data ingestion and transformation
- Contextual metadata tagging
- Model interoperability across platforms
- Secure, two-way connections between data sources and AI-powered tools[5]
The protocol enables developers to either expose their data through MCP servers or build AI applications (MCP clients) that connect to these servers.[5] Key components include:
- Protocol specification and SDKs
- Local MCP server support in Claude Desktop apps
- Open-source repository of MCP servers[5]
Adoption
Early adopters like Block and Apollo have integrated MCP into their systems, while development tools companies including Replit, Codeium, and Sourcegraph are working with MCP to enhance their platforms.[5] These integrations enable AI agents to better retrieve relevant information and produce more nuanced outputs with fewer attempts.[5]
Dhanji R. Prasanna, Chief Technology Officer at Block, stated: "Open technologies like the Model Context Protocol are the bridges that connect AI to real-world applications, ensuring innovation is accessible, transparent, and rooted in collaboration."[5]
OpenAI Adoption
In March 2025, OpenAI officially adopted the Model Context Protocol (MCP), following a decision to integrate the standard across its products, including the ChatGPT desktop app. OpenAI CEO Sam Altman announced the move, emphasizing that MCP support would be available in the OpenAI Agents SDK, with future support planned for the ChatGPT desktop app and the Responses API. This integration allows developers to connect their MCP servers to AI agents, simplifying the process of providing tools and context to large language models (LLMs).
Altman described the adoption of MCP as a step toward standardizing AI tool connectivity. Prior to OpenAI's adoption, the potential benefits of MCP had been discussed extensively within the developer community, particularly for simplifying development in multi-model environments.[6][7]
By adopting MCP, OpenAI joins other organizations such as Block, Inc., Replit, Codeium, and Sourcegraph in incorporating the protocol into their platforms. This wide adoption highlights MCP's potential to become a universal standard for AI system connectivity and interoperability.[8][9] MCP can be integrated with Microsoft Semantic Kernel,[10] and Azure OpenAI.[11] MCP servers can be deployed to Cloudflare.[12]
Implementation
Anthropic has provided pre-built MCP servers for popular enterprise systems including:
The open-source repository of MCP server implementations is available on GitHub, providing developers with examples and foundations for building custom integrations.[13]
Developers can create custom MCP servers to connect proprietary systems or specialized data sources to AI models. These custom implementations enable:
- Real-time access to private databases and internal tools
- Secure integration with sensitive business systems
- Context-aware AI responses based on organizational knowledge
- Automated workflows across multiple business applications
- Custom data processing pipelines for AI consumption
The protocol's open standard allows organizations to build tailored connections while maintaining compatibility with the broader MCP ecosystem. AI models can then leverage these custom connections to provide domain-specific assistance while respecting data access permissions.[5]
See also
Notes
- ↑ David, Emilia (November 25, 2024). "Anthropic releases Model Context Protocol to standardize AI-data integration". VentureBeat. Retrieved April 2, 2025.
- ↑ McKenzie, Chris (December 19, 2024). "Getting Started: Model Context Protocol". Medium.
- ↑ Roth, Emma (November 25, 2024). "Anthropic launches tool to connect AI systems directly to datasets". The Verge.
- ↑ "Model Context Protocol (MCP): A Guide With Demo Project". www.datacamp.com.[non-primary source needed]
- ↑ 5.00 5.01 5.02 5.03 5.04 5.05 5.06 5.07 5.08 5.09 "Introducing the Model Context Protocol". Anthropic. November 25, 2024. Retrieved April 2, 2025.[non-primary source needed]
- ↑ Wiggers, Kyle (March 25, 2025). "OpenAI adopts rival Anthropic's standard for connecting AI models to data". TechCrunch.
- ↑ Kumar, Vinay (March 26, 2025). "The open source Model Context Protocol was just updated — here's why it's a big deal". VentureBeat.
- ↑ "OpenAI Agents SDK: OpenAI MCP Integration". Github. Retrieved March 26, 2025.[non-primary source needed]
- ↑ "Request: Adopting MCP standard for accessing models across providers, simplifying development and integration". OpenAI Developer Community. 14 February 2025. Retrieved March 26, 2025.[non-primary source needed]
- ↑ Wallace, Mark (March 5, 2025). "Integrating Model Context Protocol Tools with Semantic Kernel: A Step-by-Step Guide". Semantic Kernel Dev Blog, Microsoft.
- ↑ mrajguru (March 16, 2025). "Model Context Protocol (MCP): Integrating Azure OpenAI for Enhanced Tool Integration and Prompting". AI - Azure AI services Blog, Microsoft.
- ↑ Brendan Irvine-Broque; Dina Kozlov; Glen Maddern (March 25, 2025). "Build and deploy Remote Model Context Protocol (MCP) servers to Cloudflare". The Cloudflare Blog. Cloudflare.
- ↑ "Model Context Protocol Servers". GitHub. Retrieved March 27, 2025.[non-primary source needed]
References
- Andersen, Jason (April 1, 2025). "Open-Sourcing And Accelerating Agent Adoption With MCP". Forbes.
- Edwards, Benj (April 1, 2025). "MCP: The new "USB-C for AI" that's bringing fierce rivals together". Ars Technica.
- Jackson, Fiona (March 28, 2025). "OpenAI Agents Now Support Rival Anthropic's Protocol, Making Data Access 'Simpler, More Reliable'". TechRepublic.
- Janakiram MSV (November 30, 2024). "Why Anthropic's Model Context Protocol Is A Big Step In The Evolution Of AI Agents". Forbes.
- Greiner, Lynn (November 26, 2024). "Anthropic introduces the Model Context Protocol". InfoWorld.
- Wiggers, Kyle (November 25, 2024). "Anthropic proposes a new way to connect data to AI chatbots". TechCrunch.
- Dickson, Ben (March 31, 2025). "What is Model Context Protocol (MCP)?". TechTalks.
- Masson, Colin (March 25, 2025). "Context Is the Missing Link: The Emergence of the Model Context Protocol in Industrial AI". ARC Advisory Group.
- Bastian, Matthias (November 25, 2024). "Anthropic's new open protocol lets AI systems tap into any data source". The Decoder.
- Jimin Kim; Anita Lewis; Justin Lewis; Laith Al-Saadoon; Paul Vincent; Pranjali Bhandari (April 1, 2025). "Introducing AWS MCP Servers for code assistants (Part 1)". Amazon AWS.
- Desai, Zankar (March 19, 2025). "Introducing Model Context Protocol (MCP) in Copilot Studio: Simplified Integration with AI Apps and Agents". Microsoft Copilot Studio Blog, Microsoft.
External links
- "Model Context Protocol". Github.
- "Model Context Protocol: Introduction". modelcontextprotocol.io. Retrieved April 2, 2025.
This article "Model Context Protocol" is from Wikipedia. The list of its authors can be seen in its historical and/or the page Edithistory:Model Context Protocol. Articles copied from Draft Namespace on Wikipedia could be seen on the Draft Namespace of Wikipedia and not main one.
