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.
Also called: MCP servers
By Divya Sharma · Checked Nov 15, 2026 · How we review
If the Model Context Protocol is the plug, an MCP server is the device on the other end. It wraps a service, such as a file system, a database, GitHub or Slack, and describes what it offers in a standard way.
What a server offers
- Tools: functions the model can call, each with a JSON Schema for its inputs. The model decides when to use them. - Resources: read-only data such as file contents or database schemas, chosen by the application. - Prompts: templates the user picks, often shown as slash commands.
MCP resources and prompts covers the last two in more depth.
How it runs
A local server usually runs as a child process on your machine and talks over standard input and output. A remote server runs on the web and talks over HTTP, often with OAuth sign-in. Either way, an MCP client inside the host application connects to it and lists its tools.
Example
The Filesystem server lets an agent read and write files in folders you allow. The Playwright server lets it drive a browser.
Risks
Installing a server gives the model new powers. A careless or malicious server can leak data or plant instructions in its tool descriptions, which is tool poisoning. The MCP tools directory lists reviewed servers.
Related terms
- 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.
- 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.
- MCP resources and prompts
- MCP resources and prompts are two things an MCP server can offer besides tools. Resources are pieces of data, each with a URI, that an app can add to context; prompts are reusable message templates a user chooses to run.
- 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.
- Agent skills
- Agent skills are folders of instructions, scripts and reference files, each described by a SKILL.md file, that an AI agent can discover and load only when a task needs them.
- 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.