MCP server · Developer tools
RunEcho MCP server
by inth3shadows
Lets your AI check which functions and types your code really declares, and catch edits that call things that do not exist.
RunEcho is a small helper that keeps a local map of the functions, classes and constants your code declares. It lets your AI look things up in that map instead of guessing, and it can stop an edit that calls a function your project does not actually have. It is handy if you use an AI coding assistant and want fewer invented function names landing in your files.
What is an MCP server? The 30-second version
On its own, your AI can only chat. An MCP server is a small helper program that gives your AI a new skill or a connection to something, here to a local index of your code. Once connected, your AI can ask RunEcho whether a symbol exists, what a file declares, or what changed since the last snapshot, and get a plain answer back. RunEcho runs on your own machine, needs no account and no internet, and gives the same answer every time.
What this MCP server does
You ask your AI something about your code, like whether a function exists or what changed lately. Your AI sends that question to RunEcho, which reads a local map of your project that you built earlier. RunEcho looks up the answer in that map and sends it back. Your AI then tells you the result in the chat, or uses it to avoid writing an edit that refers to something that is not there.
What you can do with it
- Check whether a function, class or constant actually exists in your code
- Find which file and line a symbol is defined in
- See what changed in your project's structure since the last snapshot
- Compare two snapshots to spot added or removed functions and classes
- Get a quick yes or no on whether your code's structure changed at all
- Stop an AI edit that calls a function your repo does not declare
- Check a commit before it lands for references to symbols that do not exist
Try asking your AI
- “Does my project declare a function called validateSnapshotChecksum?”
- “Where is the parseConfig function defined?”
- “What changed in my repo's structure since the last snapshot?”
- “Has the structure of my project changed since yesterday?”
What it gives back to you
You get short, plain answers in the chat: a yes or no, a file and line number, or a list of added and removed functions and classes. A structure check can come back as a small summary of what changed between two snapshots. When the guard stops an edit, you see a short note naming the symbol it could not find, plus a chance to approve it if the reference is legitimate.
Before you start
What you need
- The RunEcho binaries on your computer (a prebuilt download, or build from source with Go 1.26 or newer)
- One of your code folders added to RunEcho and indexed once
- An AI tool that supports MCP servers, like Claude Code or Codex
Good to know
The guard only checks simple, unqualified names like foo() or SomeType, so it will miss things like obj.method() and it can also flag a symbol that is new or defined elsewhere; treat it as one extra check, not a guarantee.
Install it with your AI
Add RunEcho MCP server to your AI, no technical skills needed
You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.
Sign in to get the install prompt
Members get a ready-made prompt that lets the Claude desktop app check RunEcho MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,361 MCP servers here for you.
Who it's for
Developers and technical teams who use an AI coding assistant and want a quick, local way to check that the code it writes refers to things that really exist.
