--- title: "What is Model Context Protocol (MCP)? · Globalmeta" description: "What is MCP? Components of the open protocol Anthropic announced in 2024, the globalmeta.net/mcp example, how to implement it and how it differs from APIs." url: https://globalmeta.net/en/glossary/model-context-protocol language: en alternate_tr: https://globalmeta.net/sozluk/model-context-protocol date_modified: 2026-09-25 publisher: Globalmeta usage: "Content may be quoted, cited and used for AI training and answers with attribution to globalmeta.net." --- Glossary / Definition # Model Context Protocol (MCP) - **Definition:** Model Context Protocol (MCP) is an open protocol, announced by Anthropic in 2024, that gives AI applications a standard way to connect to external data sources, tools and business systems. Definition ## What is MCP? For an AI assistant to reach your calendar, your files or your company database, a separate integration used to be written for every application and every system. MCP reduces those connections to one shared language: a system is prepared once as an MCP server, and every AI client that supports MCP can connect to it in the same way. In a commonly used analogy, MCP is like a USB-C port for AI applications. Anthropic announced the protocol as open source in November 2024, and during 2025 it gained support from other AI providers, developer tools and enterprise software. The protocol is based on JSON-RPC messages and is updated periodically through dated specification versions. [RAG](https://globalmeta.net/en/glossary/retrieval-augmented-generation) systems can also use MCP to reach their sources. Components ## What are its core components? - **Host and client:** The AI application the user works in (the host) and, inside it, the client that manages the connection with each server. - **Server:** A service that exposes a data source or system through MCP; it can run locally or remotely. - **Tools:** Operations the model can call, such as running a search, fetching a record or starting a task. - **Resources and prompts:** Content the model can read (resources) and ready-made workflow templates offered to the user (prompts). - **Transport layer:** stdio for local connections and Streamable HTTP for remote servers; remote servers use OAuth for authorisation. Example ## What does it look like in practice? globalmeta.net itself is an example. A read-only MCP server runs at https://globalmeta.net/mcp. It responds over Streamable HTTP without keeping sessions and requires no authentication, because it only serves public content and performs no write operations. The server has four tools: search_site, which searches the site; list_pages, which lists pages; get_page, which returns a page as Markdown; and get_contact, which provides contact details. The server also lists llms.txt, llms-full.txt and the Markdown version of every page as resources. Its server card is published at /.well-known/mcp/server-card.json. An assistant that supports MCP can therefore read the site's information directly and up to date, without imitating a browser. Measurement and practice ## How do you implement MCP? Implementation starts with scope: which data will the server reach, and will it only read or also perform write operations such as creating records? Tools are then defined with clear names, descriptions and input schemas; whether the model chooses the right tool depends on the quality of these descriptions. stdio is chosen for local use and Streamable HTTP for remote access. For servers with write access or access to personal data, authorisation, least privilege, audit logging and user confirmation are essential. The server is tested with tools such as MCP Inspector, and the protocol versions it supports are stated explicitly. Difference ## How does MCP differ from an API? An API is the interface a specific service offers on its own terms; every API has different endpoints, parameters and authentication, and every integration is written separately. MCP is a shared layer placed in front of APIs: when a client connects to a server, it learns at run time which tools exist, what they do and which inputs they expect. MCP does not replace APIs; it puts existing APIs into a form that AI models can discover and use. Designing that layer is part of our [AI-native system design and solutions](https://globalmeta.net/en/services/ai-native-system-design-and-solutions) service. ## Frequently asked questions **Does MCP only work with Claude?** No. MCP is an open protocol and is supported by AI applications, code editors and agent frameworks beyond Anthropic. An MCP server written once can be used with different clients that support the protocol. **Is it safe to run an MCP server?** Safety depends on how the server is designed. A read-only server that serves only public data carries little risk. Servers that perform write operations or access sensitive data need authorisation, least privilege, logging and user confirmation. **What is the point of a website having an MCP server?** AI assistants and agents can reach the site's content in a structured, up-to-date form without scraping pages. This helps the brand to be represented with accurate information in AI answers. ## Related reading ### Related services - [AI-Native System Design and Solutions](https://globalmeta.net/en/services/ai-native-system-design-and-solutions) — Service - [Digital Ecosystems](https://globalmeta.net/en/services/digital-ecosystems) — Service ### Related insights - [Putting a Formula 1 Car in City Traffic](https://globalmeta.net/en/insights/formula-1-city-traffic) — Insights · When the corporate world meets AI-native systems, what collides is not technology but rhythm. - [Draw the flow before you choose a product.](https://globalmeta.net/en/insights/connected-workflows) — Insights · On making clear how communication, files and team work connect to each other. - [The first step to being found: being understood.](https://globalmeta.net/en/insights/ai-visibility) — Insights · Before preparing for AI search, we look at content, links and organisation information. ### Related terms [Retrieval-Augmented Generation (RAG)](https://globalmeta.net/en/glossary/retrieval-augmented-generation) · [Generative Engine Optimisation (GEO)](https://globalmeta.net/en/glossary/generative-engine-optimization) · [Digital Ecosystem](https://globalmeta.net/en/glossary/digital-ecosystem) Next step ## Let's clarify what you have in mind. In the first conversation we clarify your current setup, the bottlenecks and what should come first. [Let's talk about your project](mailto:hello@globalmeta.net?subject=Discovery%20call%20%C2%B7%20Model%20Context%20Protocol%20%28MCP%29) [hello@globalmeta.net](mailto:hello@globalmeta.net) · [+90 850 330 10 10](tel:+908503301010) · Monumento Plaza, Floor 15 · Kartal, Istanbul