Glossary · AI

What is
MCP (Model Context Protocol)?

An open protocol for connecting LLMs to external tools, data sources, and contexts.

← Glossary
By Anish· Founder · Vedwix
·

Definition

MCP, introduced by Anthropic in late 2024, standardizes how LLM apps connect to external tools and data. Instead of writing custom integrations per LLM, developers expose data through MCP servers and any MCP-aware client (Claude, Cursor, Windsurf) can connect. By 2026, MCP has become a de-facto standard for agentic tool access.

Example

A team exposes their internal docs via an MCP server, and Claude Code can query it directly during a coding session.

How Vedwix uses MCP (Model Context Protocol) in client work

For any client whose AI agents need access to internal tools, we ship MCP servers.

Building with MCP (Model Context Protocol)?

We ship this.

If you're building with MCP (Model Context Protocol) in production, we can help — from architecture review to full implementation.

Brief us
Related terms
AI AgentAn LLM-powered system that autonomously chooses tools and takes multi-step actions.Tool UseAn LLM's ability to call external functions (search, calculator, database, etc.) during a response.Function CallingA structured way for LLMs to invoke developer-defined functions with typed arguments.
More AI terms
RAGAIFine-tuningAIEmbeddingAIVector DatabaseAIHybrid SearchAIRerankerAI

Working on a MCP (Model Context Protocol) project?

Brief Vedwix in three sentences or fewer.

Start a project