log-reflect-mcp
Captures and retrieves Markdown records for a personal recording system, enabling journaling, input tracking, search, and date-range review.
README
log-reflect-mcp
log-reflect-mcp is a local-first MCP server for a personal recording system. It gives an AI client a small, explicit interface for capturing and retrieving Markdown records while keeping the records in a separate repository.
It is designed to work with the directory conventions used by log-reflect-practice:
daily/
├── journal/{YYYY}/{YYYYMM}/
└── inputs/{YYYY}/{YYYYMM}/
practices/
Current scope
The first version intentionally exposes only four tools:
capture_journal: create or append a personal journal fragment.capture_input: save an external input as a Markdown note.get_records_by_date_range: retrieve journal and input records for review.search_records: search record contents.
The MCP server handles access and storage. Agent Skills remain responsible for judgment: how lightly to edit a journal, what belongs in an input note, how to review seven days, and when a recurring theme is ready to become a Practice.
Safety boundaries
- The source repository contains no personal records or credentials.
- The server can only read
daily/journal/anddaily/inputs/. - New records are written only inside those two directories.
- Existing input files are never silently overwritten.
- If more than one journal file exists for a date, the write stops instead of guessing.
Setup
Requirements: Node.js 22 or later.
npm install
cp .env.example .env
Set the absolute path to your records repository:
RECORDS_REPO_PATH=/absolute/path/to/log-reflect-practice
Build and start the stdio server:
npm run build
RECORDS_REPO_PATH=/absolute/path/to/log-reflect-practice npm start
Example client configuration
After building, point an MCP client at the compiled server:
{
"mcpServers": {
"log-reflect": {
"command": "node",
"args": ["/absolute/path/to/log-reflect-mcp/dist/src/server.js"],
"env": {
"RECORDS_REPO_PATH": "/absolute/path/to/log-reflect-practice",
"RECORDS_TIME_ZONE": "America/Los_Angeles"
}
}
}
}
Development
npm run check
npm test
To inspect the tools interactively:
npx @modelcontextprotocol/inspector node dist/src/server.js
Roadmap
- Add MCP resources for reading individual records.
- Add review and develop-practice prompts without moving judgment into storage code.
- Add an opt-in Git commit workflow.
- Add a GitHub-backed storage adapter.
- Add Streamable HTTP and OAuth only after the local workflow is stable.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.