Skip to content
ReviewRamble

The weekly brief

AI, reviewed, in your inbox.

  • New reviews of tools, models, MCP servers and repos, with the verdict up front
  • Re-checked prices and ratings when something changes
  • New analysis pieces as they are published

Models, agents, MCP servers and the tools actually worth your time.

One email a week. Unsubscribe with the link in any brief. How we use your email

Model Context Protocol

The Model Context Protocol (MCP) is an open standard that defines how AI applications connect to external tools, data and prompts, using JSON-RPC messages between a host application, its clients and separate servers.

Also called: MCP

By Divya Sharma · Checked Nov 15, 2026 · How we review

Before MCP, every AI app needed its own integration for every service. MCP gives them a shared plug. A service is wrapped once as an MCP server, and any application that speaks MCP can use it. The idea borrows from the Language Server Protocol, which did the same for programming languages in code editors.

How it works

The specification names three roles. The host is the AI application, such as a chat app or code editor. Inside it, an MCP client keeps a connection to one server. The server offers tools the model can call, resources that provide data, and prompts that act as templates; see MCP resources and prompts. Messages use JSON-RPC 2.0 and travel over a transport such as standard input and output for local servers or HTTP for remote ones.

Example

A developer adds a GitHub server to their coding agent. The agent can now list issues and open pull requests through tools the server exposes, without the agent's makers writing any GitHub code.

Security

The specification states that tools amount to arbitrary code execution and that hosts must get user consent before invoking them. Tool descriptions from untrusted servers can carry hidden instructions, a risk known as tool poisoning. Check what a server can do before installing it.

Browse servers in the MCP tools directory.

Related terms

MCP server
An MCP server is a program that exposes tools, data resources or prompt templates to AI applications through the Model Context Protocol, so any MCP-compatible client can use them without custom integration code.
MCP client
An MCP client is the part of an AI application that holds one connection to one MCP server, negotiating capabilities and carrying requests, results and notifications between that server and the host app.
Tool calling
Tool calling, also called function calling, is a model API feature where you describe functions with a schema, the model replies with a structured request to call one, and your code runs it and returns the result.
Agent2Agent protocol
The Agent2Agent protocol (A2A) is an open standard that lets AI agents built on different frameworks and by different vendors find each other, delegate tasks and exchange results without exposing their internal tools or memory.
MCP transport (stdio, Streamable HTTP)
An MCP transport is the channel that carries MCP's JSON-RPC messages between client and server. The specification defines two: stdio, for a server run as a local subprocess, and Streamable HTTP, for a server reached over the network.
Tool poisoning
Tool poisoning is an attack where a malicious tool, often an MCP server, hides instructions in its tool description or metadata; the AI model reads them as guidance and may leak data or misuse other tools without the user noticing.

Sources