MCP, explained: connect your AI assistant to the tools and data you already use
Five checks to run before you connect an MCP server someone else wrote: who publishes it, whether the package matches its repository, what access it asks for, what its tool descriptions tell the model, and which version will run.
"Unexpected token ... is not valid JSON" in your MCP logs means a local server printed plain text on stdout, the channel reserved for protocol messages. Here is how to find the stray line and move it to stderr, from a quick terminal test to fixing your own server code.
The official Memory MCP server stores people, projects and facts in one local file so your AI app can recall them in later chats. How it works, how to set it up, and what not to store.
The official Git MCP server lets your AI app read diffs and history, stage and commit in local repositories. What its tools do, how to set it up, and how to confine it.
A local MCP server is a program your AI app runs on your computer; a remote one is a web address you sign in to. How to tell them apart and which to pick.
Text a server fetches for your AI app can carry instructions the model may follow. Here is how prompt injection through tool output works, what the MCP specification says about it, and how to keep the damage small with approvals, narrow access and split sessions.
"spawn npx ENOENT" means your AI app could not find the npx program, usually because it does not see the folder where Node.js lives. Here is why your terminal finds it and the app does not, and the fixes from simplest to hardest, including the Windows ${APPDATA} case.
The official fetch MCP server lets your AI app read web pages as markdown. Here is what its tool and prompt do, how its private-address guard and robots.txt rules work, how to set it up, and how to limit prompt injection from the pages it reads.
The official filesystem MCP server lets your AI app read, search and edit files, but only inside the folders you allow. Here is what each tool does, how folder access works, how to set it up in Claude Desktop, VS Code or Docker, and how to keep access narrow.
The Model Context Protocol lets AI apps connect to your files, code and work tools through one standard. Here is what host, client, server, tool, resource and prompt mean, how local and remote servers differ, and how to connect them safely.
