Advertise
MCP.so
Sign In
M

Memoria MCP Server

@byronwade

Repository

Basic information

Category

Other

Transports

stdio

Author

byronwade

Submitted by

Byron Wade

About Memoria MCP Server

Prevents your AI from breaking code by revealing hidden file dependencies through git forensics.

#mcp#ai-code-assistant#git-forensics

Memoria MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "memoria": {
      "command": "npx",
      "args": [
        "-y",
        "@byronwade/memoria"
      ]
    }
  }
}

Memoria MCP Server tools

6

Returns forensic history, hidden dependencies, and risk assessment. USE THIS before modifying files.

Search git history for WHY code was written. IMPORTANT: Use SHORT, SPECIFIC KEYWORDS (e.g., 'serialization', 'race condition', 'timeout'). Do NOT use full sentences or long descriptions - they will return 0 results. Use when asking 'why does this exist?' or before removing code.

Get relevant memories and context before modifying a file. Returns memories, code graph relationships, and recent high-risk commits. Auto-saves critical discoveries when cloud is configured.

Save a lesson, context, or decision for future AI sessions. Use this when you discover important context that should be remembered.

Extract memories from code comments (IMPORTANT, WARNING, HACK, TODO, etc.). When cloud is configured, automatically saves high-confidence (>=70%) memories. Use to find and capture implicit knowledge in code.

Search extracted memories using BM25 keyword matching. FREE feature. Find relevant context from code comments using natural language queries.

Overview

What is Memoria?

Memoria is an MCP server that reveals hidden file dependencies in a codebase by analyzing git history, helping AI assistants avoid breaking code during refactoring. It targets developers using AI coding tools like Claude, Cursor, Windsurf, or Cline.

How to use Memoria?

Install via npx -y @byronwade/memoria and add the MCP server configuration to your AI tool (Claude Desktop, Cursor, etc.), then restart the tool. Ask your AI to use the analyze_file tool on any file before editing to get coupled files, risk scores, and stale dependencies.

Key features of Memoria

  • Volatility Engine – Tracks panic keywords with time-decay and bus factor.
  • Entanglement Engine – Finds files that change together >15% of the time.
  • Sentinel Engine – Detects stale dependencies (>7 days out of sync).
  • Static Import Engine – Finds explicit imports via git grep.
  • History Search (The Archaeologist) – Searches git history to understand why code was written.
  • 100% local & private – No code uploaded, no API keys needed.

Use cases of Memoria

  • Refactor a file without accidentally breaking coupled, non-imported dependencies.
  • Assess the risk of modifying a file based on historical volatility and coupling.
  • Identify stale dependents that need updating before making changes.
  • Understand why a puzzling piece of code exists before deleting or modifying it.
  • Automatically check file forensics before every edit via auto-pilot rule files.

Frequently asked questions

1

What makes Memoria different from static analysis tools?

Static analysis only finds explicit imports. Memoria uses git forensics to reveal implicit dependencies—files that change together even without imports.

2

Where does my code data go?

Memoria runs entirely on your machine. It reads your local `.git` folder directly; no code is uploaded to the cloud. Works offline and requires no API keys.

3

What dependencies or runtime are required?

You need Node.js and npm (to run `npx`) and `git` installed on your system. The server is published as an npm package `@byronwade/memoria`.

4

How do I verify Memoria is working?

After installation, ask your AI: "What MCP tools do you have available?" You should see `analyze_file` and `ask_history` in the list.

5

What transport protocol does Memoria use?

Memoria uses stdio MCP transport, as configured via the `command` and `args` fields in the MCP server JSON configuration.

Comments

More Other MCP servers

Blender

ahujasid

Open-source MCP to use Blender with any LLM

23.6K

ICSS

chokcoco

不止于 CSS

20.7K

Handl

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

Klarix Intelligence Engine

Klarix

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.

Codelf

unbug

A search tool helps dev to solve the naming things problem.

14.2K
Advertise