Paprika 3
Manage your Paprika 3 recipes with an LLM. Read, create, and update recipes in your Paprika app.
paprika-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.
Verwandte Server
Dooray MCP Server
Manage schedules using the Dooray API. Requires API key, member ID, and calendar ID to be configured.
Taiga MCP Bridge
Interact with the Taiga project management platform through an MCP bridge, allowing AI tools to manage project resources.
ClaudeKeep
Save and share AI conversations from Claude Desktop.
Linear
Integrates with Linear project management systems.
incident.io
Interact with the incident.io API to manage incidents and workflows.
Atlassian Jira
Integrates AI with Atlassian Jira to manage projects, search for issues, and view development information like commits and pull requests.
PAF-IAST LMS Automation
Automates interactions with the PAF-IAST Learning Management System (LMS) for AI assistants like Claude and VS Code Copilot.
Document Evaluation MCP Server
Evaluates technical documentation against globalization standards, analyzing for translation issues, ambiguity, and sentence length.
Folderr MCP Server
Interact with the Folderr API to manage and communicate with Folderr Assistants.
Linear MCP Server
Interact with the Linear API to manage issues, projects, and teams programmatically.