The Model Context Protocol (MCP) is an open standard and open-source framework introduced by Anthropic in November 2024 to standardize the way artificial intelligence (AI) systems like large language models (LLMs) integrate and share data with external tools, systems, and data sources. MCP provides a standardized interface for reading files, executing functions, and handling contextual prompts. Following its announcement, the protocol was adopted by major AI providers, including OpenAI and Google DeepMind.
MCP addresses the challenge of connecting AI assistants to diverse data systems such as content repositories, business management tools, and development environments. The protocol was created at Anthropic by engineers David Soria Parra and Justin Spahr-Summers. It aims to solve the problem of information silos and legacy systems that previously required custom connectors for each data source or tool, a challenge Anthropic described as an "N×M" data integration problem.
Background
MCP was announced by Anthropic in November 2024 as an open standard for connecting AI assistants to data systems. Before MCP, developers often had to build custom connectors for each data source or tool, resulting in what Anthropic described as an "N×M" data integration problem. Earlier stop-gap approaches, such as OpenAI's 2023 "function-calling" API and the ChatGPT plug-in framework, solved similar problems but required vendor-specific connectors. MCP re-uses the message-flow ideas of the Language Server Protocol (LSP).
In December 2025, Anthropic donated the MCP to the Agentic AI Foundation (AAIF), a directed fund under the Linux Foundation, co-founded by Anthropic, Block and OpenAI, with support from other companies. Later that month, Anthropic also published Agent Skills, a companion open standard for packaging task-specific instructions and resources that AI agents load on demand, following the same open-standard approach as MCP.
Features
MCP defines a standardized framework for integrating AI systems with external data sources and tools. The protocol enables applications such as querying structured databases with plain language in the field of natural language data access.
The protocol distinguishes between MCP hosts, MCP clients and MCP servers. An MCP host is typically an AI agent that interacts with an LLM and requires services from one or more MCP servers. For each of these MCP servers, the MCP host will create a dedicated MCP client that communicates with that server. Client and host will typically run on the same machine, while the MCP servers may be local or remote.
Each server provides one or more tools or resources. Example tools include access to a database, calculators, and access to code repositories; a resource might be a certain FAQ document. The MCP client asks its server for a list of tools and resources the server provides; the server replies with a natural-language description of the capabilities of each tool and the expected format to call the tool. This information is given to the LLM; if it requires the services of one of these tools, the MCP host will instruct the relevant MCP client to call the tool. The MCP server performs the tool action and returns the results, which the MCP host then injects into the LLM conversation. Client and server communicate using the JSON-RPC 2.0 transport protocol.
The protocol was released with software development kits (SDKs) in programming languages including Python, TypeScript, C# and Java and examples of MCP server implementations.
The protocol is used in AI-assisted software development tools. Integrated development environments (IDEs), coding platforms such as Replit, and code intelligence tools like Sourcegraph have adopted MCP to grant AI coding assistants real-time access to project context.
MCP Apps is an official extension to the Model Context Protocol built on mcp-ui. While the base MCP specification is restricted to text and structured data, MCP Apps standardizes the delivery of interactive user interfaces, such as dashboards, forms, and data visualizations, from MCP servers to host applications like Claude and ChatGPT.
Adoption
In March 2025, OpenAI officially adopted the MCP, after having integrated the standard across its products, including the ChatGPT desktop app. In September 2025, OpenAI added support for MCP to ChatGPT apps, allowing for third-party access inside ChatGPT.
MCP can be integrated with Microsoft Semantic Kernel and Azure OpenAI. MCP servers can be deployed to Cloudflare. The protocol has also been adopted by Google DeepMind and other major AI providers.
In April 2026, the AAIF held the MCP Dev Summit North America in New York City, drawing approximately 1,200 attendees. That same month, Salesforce's Headless 360 platform began routing customer and agent interactions via MCP; in late May, Salesforce reported 4.5 million MCP calls had been processed since launch.
By mid-2026, more than 10,000 MCP servers had reportedly been deployed in production, with the protocol's SDKs downloaded over 97 million times per month.
2026-07-28 revision
On July 28, 2026, MCP's maintainers finalized a major revision of the specification, described by Anthropic technical staff member David Soria Parra as the most substantial change to the protocol since the addition of authorization. The revision removes protocol-level session tracking, making MCP stateless at the protocol layer: information about protocol version, client identity, and capabilities is instead carried in a _meta parameter with each request. The change brings MCP's request model closer to that of Anthropic's own Claude Messages API.
The revision also deprecated several features that had seen limited use, including sampling (allowing a server to request a completion from the client's model) and roots (allowing clients to indicate relevant file-system locations to a server); deprecated features remain functional for a minimum of twelve months. Some previously core functionality, such as the Tasks feature for long-running operations, was moved out of the base protocol and into optional extensions. Not all of the changes are backward compatible, and servers implementing the new revision may not interoperate with older clients without a compatibility layer.
Reception
The Verge reported that MCP addresses a growing demand for AI agents that are contextually aware and capable of pulling from diverse sources. The protocol has been likened to OpenAPI, a similar specification that aims to describe APIs.
In April 2025, security researchers released an analysis that concluded there are multiple outstanding security issues with MCP, including prompt injection and poisoned tools that allow for data exfiltration through other connected tools. These concerns highlight the ongoing challenges in securing AI-tool integration frameworks.
Impact on AI Ecosystem
The growth of MCP has significant implications for the broader artificial intelligence ecosystem. By standardizing how large language models connect to external tools, MCP reduces the friction for developers building AI-powered applications. The protocol's adoption by major cloud providers and AI companies has accelerated the development of interoperable AI tools.
MCP's open-standard approach aligns with efforts to democratize access to AI capabilities. The protocol's support for multiple programming languages and its extensible architecture have made it accessible to a wide range of developers. The establishment of the AAIF under the Linux Foundation provides governance and long-term stewardship for the protocol's development.
The protocol's evolution reflects broader trends in generative AI, particularly the shift from standalone models to integrated systems that can interact with real-world data and services. As AI agents become more sophisticated, standards like MCP play a crucial role in enabling seamless interoperability across platforms and tools.
See Also
- Agent2Agent - Open protocol for communication between AI agents
- AI governance
- Application programming interface
- LangChain - Language model application development framework
- Machine learning
- Open weights
- Software agent
- Retrieval-augmented generation