Login
Login

Draft:Model Context Protocol

{{Short description|Open-source AI tool standards}}

{{Draft topics|internet-culture|software|computing|technology}}

{{AfC topic|stem}}

{{AfC submission|||ts=20250402191239|u=174.17.179.188|ns=118}}

{{AFC submission|d|neo|u=MasterZig|ns=118|decliner=Caleb Stanford|declinets=20250328002426|ts=20250327001958}}

{{AFC submission|d|nn|u=2600:1700:9850:45E0:34EA:E5B5:23CB:21AC|ns=118|decliner=Beachweak|declinets=20250102020925|small=yes|ts=20250102020409}}

{{AFC comment|1=Fails WP:TOOSOON IMO. I don't doubt that this is an important protocol or may be at some point in the future, but the current sources are mostly primary and don't demonstrate that the protocol is considered of general importance beyond Anthropic and [https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=%22model+context+protocol%22&btnG= a few notes] on Google Scholar. While I don't think it yet merits an article, could be worth a mention at Prompt engineering or similar. Caleb Stanford (talk) 00:24, 28 March 2025 (UTC)}}

{{AFC comment|1=GitHub and primary sources about the software are unreliable, as they are made up of user-generated content. Please find other sources to establish notability and expand the article in order to get it published. Beachweak (talk) 02:09, 2 January 2025 (UTC)}}

----

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.{{cite news |first= Emilia |last= David |date= November 25, 2024 |title= Anthropic releases Model Context Protocol to standardize AI-data integration |publisher= VentureBeat |url= https://venturebeat.com/data-infrastructure/anthropic-releases-model-context-protocol-to-standardize-ai-data-integration/ |access-date= April 2, 2025}} 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.{{cite web |first= Chris |last= McKenzie |date= December 19, 2024 |title= Getting Started: Model Context Protocol |website= Medium |url= https://medium.com/@kenzic/getting-started-model-context-protocol-e0a80dddff80 }}

Background

The protocol was announced in November 2024{{cite news |first= Emma |last= Roth |date= November 25, 2024 |title= Anthropic launches tool to connect AI systems directly to datasets |publisher= The Verge |url= https://www.theverge.com/2024/11/25/24305774/anthropic-model-context-protocol-data-sources }} as an open-source{{Cite web |url= https://www.datacamp.com/tutorial/mcp-model-context-protocol |title= Model Context Protocol (MCP): A Guide With Demo Project |website= www.datacamp.com}}{{primary-inline}} standard for connecting AI assistants to systems where data lives, including content repositories, business tools, and development environments.{{cite web |url= https://www.anthropic.com/news/model-context-protocol |title= Introducing the Model Context Protocol |publisher= Anthropic |date= November 25, 2024 |access-date= April 2, 2025}}{{primary-inline}} It addresses the challenge of information silos and legacy systems that constrain even the most sophisticated AI models.

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

The protocol enables developers to either expose their data through MCP servers or build AI applications (MCP clients) that connect to these servers. Key components include:

  • Protocol specification and SDKs
  • Local MCP server support in Claude Desktop apps
  • Open-source repository of MCP servers

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. These integrations enable AI agents to better retrieve relevant information and produce more nuanced outputs with fewer attempts.

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."

= 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.{{cite news |first= Kyle |last= Wiggers |date= March 25, 2025 |title= OpenAI adopts rival Anthropic's standard for connecting AI models to data |publisher= TechCrunch |url= https://techcrunch.com/2025/03/26/openai-adopts-rival-anthropics-standard-for-connecting-ai-models-to-data/ }}{{cite news |first= Vinay |last= Kumar |date= March 26, 2025 |title= The open source Model Context Protocol was just updated — here's why it's a big deal |publisher= VentureBeat |url= https://venturebeat.com/ai/the-open-source-model-context-protocol-was-just-updated-heres-why-its-a-big-deal/ }}

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.{{Cite web |title= OpenAI Agents SDK: OpenAI MCP Integration |url=https://openai.github.io/openai-agents-python/mcp/ |website= Github |access-date=March 26, 2025}}{{primary-inline}}{{Cite web |title= Request: Adopting MCP standard for accessing models across providers, simplifying development and integration |publisher= OpenAI Developer Community |url= https://community.openai.com/t/request-adopting-mcp-standard-for-accessing-models-across-providers/1120641 |access-date= March 26, 2025}}{{primary-inline}} MCP can be integrated with Microsoft Semantic Kernel, {{Cite web |url= https://devblogs.microsoft.com/semantic-kernel/integrating-model-context-protocol-tools-with-semantic-kernel-a-step-by-step-guide/ |title= Integrating Model Context Protocol Tools with Semantic Kernel: A Step-by-Step Guide |first= Mark |last= Wallace |date= March 5, 2025 |website= Semantic Kernel Dev Blog, Microsoft }} and Azure OpenAI. {{cite web |author1= mrajguru |date= March 16, 2025 |title= Model Context Protocol (MCP): Integrating Azure OpenAI for Enhanced Tool Integration and Prompting |website= AI - Azure AI services Blog, Microsoft |url= https://techcommunity.microsoft.com/blog/azure-ai-services-blog/model-context-protocol-mcp-integrating-azure-openai-for-enhanced-tool-integratio/4393788 }} MCP servers can be deployed to Cloudflare.{{cite web |author1= Brendan Irvine-Broque |author2= Dina Kozlov |author3= Glen Maddern |date= March 25, 2025 |title= Build and deploy Remote Model Context Protocol (MCP) servers to Cloudflare |publisher= Cloudflare |url= https://blog.cloudflare.com/remote-model-context-protocol-servers-mcp/ }}

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.{{cite web |url=https://github.com/modelcontextprotocol/servers |title=Model Context Protocol Servers |website=GitHub |access-date=March 27, 2025}}{{primary-inline}}

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.

See also

Notes

{{reflist}}

References

  • {{cite news |first= Jason |last= Andersen |date= April 1, 2025 |title= Open-Sourcing And Accelerating Agent Adoption With MCP |work= Forbes |url= https://www.forbes.com/sites/moorinsights/2025/04/01/open-sourcing-and-accelerating-agent-adoption-with-mcp/ }}
  • {{cite news |first= Benj |last= Edwards |date= April 1, 2025 |title= MCP: The new "USB-C for AI" that's bringing fierce rivals together |publisher= Ars Technica |url= https://arstechnica.com/information-technology/2025/04/mcp-the-new-usb-c-for-ai-thats-bringing-fierce-rivals-together }}
  • {{cite news |first= Fiona |last= Jackson |date= March 28, 2025 |title= OpenAI Agents Now Support Rival Anthropic's Protocol, Making Data Access 'Simpler, More Reliable' |publisher= TechRepublic |url= https://www.techrepublic.com/article/news-openai-anthropic-model-context-protocol/ }}
  • {{cite news |author= Janakiram MSV |date= November 30, 2024 |title= Why Anthropic's Model Context Protocol Is A Big Step In The Evolution Of AI Agents |work= Forbes |url= https://www.forbes.com/sites/janakirammsv/2024/11/30/why-anthropics-model-context-protocol-is-a-big-step-in-the-evolution-of-ai-agents/ }}
  • {{cite news |first= Lynn |last= Greiner |date= November 26, 2024 |title= Anthropic introduces the Model Context Protocol |publisher= InfoWorld |url= https://www.infoworld.com/article/3613143/anthropic-introduces-the-model-context-protocol.html }}
  • {{cite news |first= Kyle |last= Wiggers |date= November 25, 2024 |title= Anthropic proposes a new way to connect data to AI chatbots |publisher= TechCrunch |url= https://techcrunch.com/2024/11/25/anthropic-proposes-a-way-to-connect-data-to-ai-chatbots/ }}
  • {{cite web |first= Ben |last= Dickson |date= March 31, 2025 |title= What is Model Context Protocol (MCP)? |publisher= TechTalks |url= https://bdtechtalks.com/2025/03/31/model-context-protocol-mcp/?utm_source=rss&utm_medium=rss&utm_campaign=model-context-protocol-mcp }}
  • {{cite web |first= Colin |last= Masson |date= March 25, 2025 |title= Context Is the Missing Link: The Emergence of the Model Context Protocol in Industrial AI |publisher= ARC Advisory Group |url= https://www.arcweb.com/blog/context-missing-link-emergence-model-context-protocol-industrial-ai }}
  • {{cite web |first= Matthias |last= Bastian |date= November 25, 2024 |title= Anthropic's new open protocol lets AI systems tap into any data source |publisher= The Decoder |url= https://the-decoder.com/anthropics-new-open-protocol-lets-ai-systems-tap-into-any-data-source/}}
  • {{cite web |author1= Jimin Kim |author2= Anita Lewis |author3= Justin Lewis |author4= Laith Al-Saadoon |author5= Paul Vincent |author6= Pranjali Bhandari |title= Introducing AWS MCP Servers for code assistants (Part 1) |date= April 1, 2025 |publisher= Amazon AWS |url= https://aws.amazon.com/blogs/machine-learning/introducing-aws-mcp-servers-for-code-assistants-part-1/ }}
  • {{cite web |first= Zankar |last= Desai |date= March 19, 2025 |title= Introducing Model Context Protocol (MCP) in Copilot Studio: Simplified Integration with AI Apps and Agents |publisher= Microsoft Copilot Studio Blog, Microsoft |url= https://www.microsoft.com/en-us/microsoft-copilot/blog/copilot-studio/introducing-model-context-protocol-mcp-in-copilot-studio-simplified-integration-with-ai-apps-and-agents/ }}

External links

  • {{cite web |url= https://github.com/modelcontextprotocol |title= Model Context Protocol |website= Github }}
  • {{cite web |url= https://modelcontextprotocol.io/introduction |title= Model Context Protocol: Introduction |website= modelcontextprotocol.io |access-date= April 2, 2025}}

:Category:Artificial intelligence

:Category:Open standards