claude-memory-mcp
An MCP server that gives Claude Code cross-session memory persisted to a plain .claude-memory.md file in your repo.
README
claude-memory-mcp
An MCP server that gives Claude Code cross-session memory — persisted to a plain .claude-memory.md file inside your repo.
Each project gets its own memory. Commit the file to git and it follows the codebase forever.
Install
# Via uvx (no install needed)
uvx claude-memory-mcp
# Or pip
pip install claude-memory-mcp
Configure Claude Code
Add to your project's .mcp.json (or ~/.claude.json for global):
{
"mcpServers": {
"memory": {
"command": "uvx",
"args": ["claude-memory-mcp"]
}
}
}
Tools
| Tool | Description |
|---|---|
memory_read(key) |
Read a stored value |
memory_write(key, value) |
Write a value |
memory_list() |
List all keys |
How it works
Memory is stored as ## sections in .claude-memory.md at your repo root:
# Claude Memory
## architecture-decisions
We use SQLite for local dev and Postgres in prod.
Decided 2025-01-15 — migration too risky mid-sprint.
## current-sprint-context
Working on payment webhook handler. Stripe sends events
to /api/webhooks/stripe. See stripe_handler.py:42.
- Project-scoped: different repos = different memory files
- Git-tracked: commit
.claude-memory.md— memory persists across machines and teammates - Human-readable: open the file, edit it, diff it like any other source file
- No auth, no cloud, no database: just a file
Use cases
- Remember architectural decisions across sessions
- Store "where I left off" context so Claude doesn't ask again
- Share team conventions without repeating them in every prompt
- Track ongoing debugging context across long refactors
Show HN post
Show HN: I built an MCP server that gives Claude Code a persistent memory file
The problem: every Claude Code session starts fresh. I keep explaining the same architectural decisions, the same "don't touch X" rules, the same "we use Y for Z" conventions.
This MCP server persists memory to
.claude-memory.md— a plain markdown file in your repo. Claude reads and writes it across sessions. Commit it to git and it follows the codebase.Three tools:
memory_read,memory_write,memory_list. That's it.Install: add 8 lines to your
.mcp.json, runuvx claude-memory-mcp.
License
MIT
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.