About paprika-3-mcp
paprika-3-mcp is an MCP server that exposes Paprika 3 recipes as LLM-readable resources and lets an LLM create or update recipes in the Paprika app. It is aimed at Paprika 3 users who want to manage recipes through natural language.
Key features
- 01Recipes exposed as readable resources
- 02Tool for creating new recipes
- 03Tool for updating existing recipes
- 04Supports macOS, Linux and Windows
- 05Installable via Homebrew or prebuilt binaries
Use cases
- 01Adding new recipes through Claude using natural language
- 02Letting an LLM modify saved recipes during a conversation
- 03Giving an LLM access to recipe content to answer questions
MCP support
The server exposes Paprika 3 recipes as MCP resources and provides the create_paprika_recipe and update_paprika_recipe tools to MCP clients such as Claude.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEpaprika-3-mcp
A Model Context Protocol (MCP) server that exposes your Paprika 3 recipes as LLM-readable resources — and lets an LLM like Claude create or update recipes in your Paprika app.
🖼️ Example: Claude using the Paprika MCP server
🚀 Features
See anything missing? Open an issue on this repo to request a feature!
📄 Resources
- Recipes ✅
- Recipe Photos 🚧
🛠 Tools
create_paprika_recipe
Allows Claude to save a new recipe to your Paprika appupdate_paprika_recipe
Allows Claude to modify an existing recipe
⚙️ Prerequisites
- ✅ A Mac, Linux, or Windows system
- ✅ Paprika 3 installed with cloud sync enabled
- ✅ Your Paprika 3 username and password
- ✅ Claude or any LLM client with MCP tool support enabled
🛠 Installation
You can download a prebuilt binary from the Releases page.
🍎 macOS (via Homebrew)
If you're on macOS, the easiest way to install is with Homebrew:
brew tap soggycactus/tap
brew install paprika-3-mcp
🐧 Linux / 🪟 Windows
-
Go to the latest release.
-
Download the appropriate archive for your operating system and architecture:
paprika-3-mcp_<version>_linux_amd64.zipfor Linuxpaprika-3-mcp_<version>_windows_amd64.zipfor Windows
-
Extract the zip archive:
- Linux:
unzip paprika-3-mcp_<version>_<os>_<arch>.zip - Windows:
- Right-click the
.zipfile and select Extract All, or use a tool like 7-Zip.
- Right-click the
- Linux:
-
Move the binary to a directory in your system's
$PATH:-
Linux:
sudo mv paprika-3-mcp /usr/local/bin/ -
Windows:
- Move
paprika-3-mcp.exeto any folder in yourPATH(e.g.,%USERPROFILE%\bin)
- Move
-
✅ Test the installation
You can verify the server is installed by checking:
paprika-3-mcp --version
You should see:
paprika-3-mcp version v0.1.0
🤖 Setting up Claude
If you haven't setup MCP before, first read more about how to install Claude Desktop client & configure an MCP server.
To add paprika-3-mcp to Claude, all you need to do is create another entry in the mcpServers section of your claude_desktop_config.json file:
{
"mcpServers": {
"paprika-3": {
"command": "paprika-3-mcp",
"args": [
"--username",
"<your paprika 3 username (usually email)>",
"--password",
"<your paprika 3 password>"
]
}
}
}
Restart Claude and you should see the MCP server tools after clicking on the hammerhead icon:

📄 License
This project is open source under the MIT License © 2025 Lucas Stephens.
🗂 Miscellaneous
📄 Where can I see the server logs?
The MCP server writes structured logs using Go’s slog with rotation via lumberjack. Log files are automatically created based on your operating system:
| Operating System | Log File Path |
|---|---|
| macOS | ~/Library/Logs/paprika-3-mcp/server.log |
| Linux | /var/log/paprika-3-mcp/server.log |
| Windows | %APPDATA%\paprika-3-mcp\server.log |
| Other / Unknown | /tmp/paprika-3-mcp/server.log |
💡 Logs are rotated automatically at 100MB, with only 5 backup files kept. Logs are also wiped after 10 days.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.