Happy slice of mcp pizzaMCP.pizza

jinni

MCP.Pizza Chef: smat-dev

Instead of making the assistant open one file at a time, Jinni hands it a single bundle of everything relevant in a folder, skipping binaries, hidden files, logs, and build output, and honouring the ignore rules you already have. A command-line version copies the same bundle to your clipboard for pasting into any chat window. It only reads: it cannot edit, create, or delete anything. No account or key is required, and development has been quiet since December 2025.

Coding
Files/PDF

Use This MCP server To

Load my whole codebase into the assistant in one go Ask for a plain-English tour of an unfamiliar project Pull in just the tests folder instead of everything Copy my project's contents to the clipboard for any chat window List which files would be included before sending them Narrow what the assistant sees when a project is too big

README

Jinni Banner

Jinni: Bring Your Project Into Context

Jinni: Bring Your Project Into Context MCP server

Jinni is a tool to efficiently provide Large Language Models the context of your projects. It gives a consolidated view of relevant project files, overcoming the limitations and inefficiencies of reading files one by one. Each file's content is preceded by a simple header indicating its path:

```path=src/app.py
print("hello")

The philosophy behind this tool is that LLM context windows are large, models are smart, and directly seeing your project best equips the model to help with anything you throw at it.

There is an MCP (Model Context Protocol) server for integration with AI tools and a command-line utility (CLI) for manual use that copies project context to the clipboard ready to paste wherever you need it.

These tools are opinionated about what counts as relevant project context to best work out of the box in most use cases, automatically excluding:

* Binary files
* Dotfiles and hidden directories
* Common naming conventions for logs, build directories, tempfiles, etc

Inclusions/exclusions are customizable with complete granularity if required using .contextfiles – this works like .gitignore except defining inclusions. .gitignore files themselves are also respected automatically, but any rules in .contextfiles take priority.

The MCP server can provide as much or as little of the project as desired. By default the scope is the whole project, but the model can ask for specific modules / matching patterns / etc.

MCP Quickstart

MCP server config file for Cursor / Roo / Claude Desktop / client of choice:

{
    "mcpServers": {
        "jinni": {
            "command": "uvx",
            "args": ["jinni-server"]
        }
    }
}

You can optionally constrain the server to only read within a tree for security in case your LLM goes rogue: add "--root", "/absolute/path/" to the args list.

Install uv if it is not on your system: https://docs.astral.sh/uv/getting-started/installation/

Reload your IDE and you can now ask the agent to read in context.

If you want to restrict this to particular modules / paths just ask - e.g. "Read context for tests".

In action with Cursor:

Usage Example

Note For Cursor Users

Cursor can silently drop context that is larger than the allowed maximum, so if you have a sizable project and the agent acts like the tool call never happened, try reducing what you are bringing in ("read context for xyz")

jinni FAQ

Can I use this to have my assistant rewrite my files?
No. It is strictly read-only, offering a single tool that gathers and returns file contents. Any editing has to be done by another tool or by you.
Do I need an account or a key?
No. It runs entirely on your own machine and never talks to a paid service.
Which apps does it work in?
Cursor, Claude Desktop, Cline, Roo, and VS Code are all named in the project, and anything accepting a standard MCP configuration should work.
How hard is the setup?
You install the uv runner once, then paste a three-line block into your assistant's settings. No building or coding is involved.
Is it still being updated?
The last code change was in December 2025, so it has been quiet for several months. It still installs and runs as documented.
What if my project is too large to send?
It stops with a clear message listing the ten biggest files, and you can then ask for a specific folder instead of the whole thing.
Can I stop it from reading sensitive folders?
Yes. You can lock it to a single directory when you set it up, and it respects your existing ignore rules.