- Home
- MCP servers
- MCP-DayOne
MCP-DayOne
- python
15
GitHub Stars
python
Language
6 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"quevin-mcp-dayone": {
"command": "uv",
"args": [
"--directory",
"/FULL/PATH/TO/mcp-dayone",
"run",
"python",
"-m",
"mcp_dayone.server"
]
}
}
}This MCP server lets Claude Desktop talk to your Day One journals. It handles writing entries through the Day One CLI and reads data directly from the Day One database, enabling natural language interactions for creating, listing, and inspecting journal content with rich metadata and attachments.
How to use
You interact with the Day One MCP server through Claude Desktop. After you configure the MCP server, you can command Claude to write journal entries, attach media, add locations, search entries by text, and list journals with counts. Use natural language prompts like: create a journal entry with photos, show me my recent entries, or what were my entries on this day. The server bridges your Claude conversations with both Day One writing capabilities and direct read access to the Day One database for rich results.
How to install
Prerequisites: Day One CLI, Python 3.11+, and uv.
# Install uv package manager (if not already installed)
curl -LsSf https://astral.sh/uv/install.sh | sh
# Verify Day One CLI is accessible
dayone2 --version
# Verify Day One CLI is accessible
dayone2 --version
Configure Claude Desktop
Add to your Claude Desktop configuration a single MCP server entry that points to the local MCP process.
{
"mcpServers": {
"dayone": {
"command": "uv",
"args": [
"--directory",
"/FULL/PATH/TO/mcp-dayone",
"run",
"python",
"-m",
"mcp_dayone.server"
]
}
}
}
Run and test the server
Validate the setup and ensure the server runs correctly.
# Build-time validation is not required for manual steps here; run the test setup if you have it configured
uv run python test_setup.py
Usage notes
- The server uses a hybrid approach: write operations go through the Day One CLI, while read operations access the Day One SQLite database for metadata and counts. - The MCP server is designed to work out of the box with minimal changes; you mainly need to point to the correct directory where the MCP Day One project resides.
Available tools
create_journal_entry
Create entries with metadata, attachments, location, and tags via Day One CLI.
create_entry_with_attachments
Attach photos, videos, audio, PDFs to new entries.
create_location_entry
Create location-aware entries with coordinates.
read_recent_entries
Read recent entries with full metadata from the Day One database.
search_entries
Search entries by text content across journals.
list_journals_from_db
List actual journals with entry counts and statistics from the database.
get_entry_count_from_db
Get real entry counts for journals from the database.
get_entries_by_date
Retrieve "On This Day" entries across previous years with full content.