paprika-3-mcp
MCP Server for creating/editing recipes in Paprika 3 with natural language
Documentation
paprika-3-mcp
A Model Context Protocol (MCP) server that exposes your Paprika 3 recipes as LLM-readable resources โ and lets an LLM like Claude create or update recipes in your Paprika app.
๐ผ๏ธ Example: Claude using the Paprika MCP server
๐ Features
See anything missing? Open an issue on this repo to request a feature!
๐ Resources
- Recipes โ
- Recipe Photos ๐ง
๐ Tools
- `create_paprika_recipe`
Allows Claude to save a new recipe to your Paprika app
- `update_paprika_recipe`
Allows Claude to modify an existing recipe
โ๏ธ Prerequisites
- โ A Mac, Linux, or Windows system
- โ Paprika 3 installed with cloud sync enabled
- โ Your Paprika 3 username and password
- โ Claude or any LLM client with MCP tool support enabled
๐ Installation
You can download a prebuilt binary from the Releases page.
๐ macOS (via Homebrew)
If you're on macOS, the easiest way to install is with Homebrew:
brew tap soggycactus/tap
brew install paprika-3-mcp๐ง Linux / ๐ช Windows
1. Go to the latest release.
2. Download the appropriate archive for your operating system and architecture:
3. Extract the zip archive:
unzip paprika-3-mcp___.zip4. Move the binary to a directory in your system's `$PATH`:
sudo mv paprika-3-mcp /usr/local/bin/โ Test the installation
You can verify the server is installed by checking:
paprika-3-mcp --versionYou should see:
paprika-3-mcp version v0.1.0๐ค 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",
"",
"--password",
""
]
}
}
}Restart Claude and you should see the MCP server tools after clicking on the hammerhead icon:

๐ License
This project is open source under the MIT License ยฉ 2025 Lucas Stephens.
๐ Miscellaneous
๐ Where can I see the server logs?
The MCP server writes structured logs using Goโs `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` |
> ๐ก Logs are rotated automatically at 100MB, with only 5 backup files kept. Logs are also wiped after 10 days.
Frequently asked questions
What is paprika-3-mcp?
paprika-3-mcp is MCP Server for creating/editing recipes in Paprika 3 with natural language
How do I install paprika-3-mcp?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is paprika-3-mcp open source?
Yes โ it is hosted on GitHub at https://github.com/soggycactus/paprika-3-mcp and has 38 stars.
Related MCP tools
eBPF-powered network observability for Kubernetes. Indexes L4/L7 traffic with full K8s context, decrypts TLS without keys. Queryable by AI agents via MCP and humans via dashboard.
GOWA - WhatsApp REST API with support for UI, Multi Account, Webhooks, and MCP, and Chatwoot. Built with Golang for efficient memory use.
The missing open-source Kubernetes UI with a built-in MCP server for AI agents. See what's broken, why, and what changed. Issues, Topology, event timeline, Helm, GitOps, live service traffic, and cluster audits - all in one Go binary.
mcp-language-server gives MCP enabled clients access semantic tools like get definition, references, rename, and diagnostics.
The Terraform MCP Server provides seamless integration with Terraform ecosystem, enabling advanced automation and interaction capabilities for Infrastructure as Code (IaC) development.
Run MATLABยฎ using AI applications with the official MATLAB MCP Server from MathWorksยฎ. This MCP server for MATLAB supports a wide range of coding agents like Claude Codeยฎ and Visual Studioยฎ Code.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP