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 systems, particularly large language models (LLMs), integrate and share data with external tools, systems, and data sources.
Overview
MCP was announced by Anthropic in November 2024 as a solution to what the company described as an "N×M" data integration problem—where developers previously had to build custom connectors for each combination of AI model and data source. The protocol was created by Anthropic engineers David Soria Parra and Justin Spahr-Summers, and reuses message-flow concepts from the Language Server Protocol (LSP).
In December 2025, Anthropic donated 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.
Architecture
MCP distinguishes between three core components:
- MCP Host: Typically an AI agent that interacts with an LLM and requires services from one or more MCP servers.
- MCP Client: A dedicated client created by the host for each MCP server it communicates with.
- MCP Server: Provides one or more tools (e.g., database access, calculators, code repositories) or resources (e.g., FAQ documents).
Communication between client and server uses the JSON-RPC 2.0 transport protocol. The server advertises its capabilities via natural-language descriptions, which the LLM can use to decide when to invoke a tool.
Features
- Standardized interface for reading files, executing functions, and handling contextual prompts
- Software Development Kits (SDKs) in Python, TypeScript, C#, Java, Kotlin, Go, PHP, Perl, Ruby, Rust, and Swift
- MCP Apps extension for delivering interactive user interfaces (dashboards, forms, data visualizations) from MCP servers to host applications
Adoption
Following its announcement, MCP was adopted by major AI providers:
- OpenAI adopted MCP in March 2025 and added support to ChatGPT apps in September 2025.
- Google DeepMind embraced the standard in April 2025.
- Microsoft integrated MCP with Semantic Kernel and Azure OpenAI.
- Salesforce routed customer and agent interactions via MCP through its Headless 360 platform.
- IDEs and coding platforms such as Replit and Sourcegraph adopted MCP for AI coding assistants.
Reception and Security
The Verge reported that MCP addresses a growing demand for contextually aware AI agents. The protocol has been likened to OpenAPI for its role in standardizing API descriptions.
In April 2025, security researchers identified outstanding security issues with MCP, including prompt injection and poisoned tools that could allow data exfiltration through connected tools.
References
- David, Emilia (November 25, 2024). "Anthropic releases Model Context Protocol to standardize AI-data integration". VentureBeat.
- Wiggers, Kyle (March 25, 2025). "OpenAI adopts rival Anthropic's standard for connecting AI models to data". TechCrunch.
- Edwards, Benj (April 1, 2025). "MCP: The new 'USB-C for AI' that's bringing fierce rivals together". Ars Technica.
- Wikipedia: Model Context Protocol
Mycenology
Mycenology is the study of the Mycenaean Greek language and the culture and institutions recorded in that language. It emerged as a discipline auxiliary to classical philology in 1953, following the deciphering of the Minoan Linear B script by Alice Kober, Michael Ventris, and John Chadwick.
Overview
Mycenology focuses on the language and administrative records of the Mycenaean civilization of Late Bronze Age Greece (circa 1450–1200 BC), which are preserved primarily in Linear B inscriptions. These inscriptions, found on clay tablets at palatial sites such as Mycenae, Pylos, Knossos, and Thebes, document the economic, socio-political, religious, and administrative structures of Mycenaean palatial societies.
The decipherment of Linear B in 1953 was a landmark achievement. Alice Kober laid the groundwork through her analysis of the script's patterns, while Michael Ventris—building on Kober's work—demonstrated that Linear B encoded an early form of Greek. John Chadwick subsequently helped refine and publish the decipherment.
Significance
Mycenology provides critical insight into:
- The earliest attested form of the Greek language (Mycenaean Greek)
- The administrative and economic organization of Late Bronze Age palatial centers
- Religious practices, trade networks, and social hierarchies of Mycenaean Greece
- The prehistory of classical Greek civilization
The most famous artifact associated with Mycenaean Greece is the Mask of Agamemnon, a gold funerary mask discovered in Grave Circle A at Mycenae, dating to the 16th century BC.
References
- Burns, Bryan E. (2010). Mycenaean Greece, Mediterranean Commerce and the Formation of Identity. Cambridge University Press.
- Brown, W. Edward (1960). "An Introduction to Mycenology". The Classical World 53 (6): 186–191.
- "Cracking the code: the decipherment of Linear B 60 years on". University of Cambridge, 2012.
- Wikipedia: Mycenology