Mimir's Vault

Key Pillars • System Architecture • Installation • MCP Client Setup • Tool Reference • Agent Workflow Guide

The Problem: Wandering AI Coding Agents

When AI coding agents (Claude Code, Cursor, Antigravity) work on complex software repositories, they frequently suffer from Context Inflation & Wandering:

• They blindly grep directories, re-scan full codebases, and load 30+ unrelated files into memory.

• They waste thousands of LLM tokens, increase execution latency, and lose track of core architectural rules.

Related MCP server: knitbrain

The Solution: Mímir's Vault Memory Graph

Mímir's Vault (Mimirs_Vault) is a high-performance Model Context Protocol (MCP) server built in Python (FastMCP).

It maintains a human-readable, interlinked Obsidian-Wikilink memory graph inside ./.context/ for any software repository.

AI agents follow the Memory-First Scanning Rule:

1. Inspect .context/overview.md via get_root_node.

2. Follow Obsidian wikilinks ([[modules/auth]]).

3. Inspect only the targeted source code files mapped in that module note.

4. Edit zero unnecessary files.

Key Pillars

System Architecture

<your-project-root>/
└── .context/                        <-- Memory Graph Root (Ignored in .gitignore)
    ├── overview.md                  <-- ROOT NODE (Scope, File Structure Map, [[modules/*]] index)
    ├── decisions.md                 <-- Architectural Decision Records (ADRs)
    └── modules/                     <-- LINKED MODULE NODES
        ├── auth.md                  <-- Module Note (Scope, Mapped Source Files)
        ├── database.md              <-- Module Note
        └── ui/                      <-- Submodule Directory
            └── components.md        <-- Submodule Note ([[modules/ui/components]])

Installation

Prerequisites

• Python 3.10+

1. Clone the Repository & Initialize Environment

# Clone repository
git clone https://github.com/GopikChenth/Mimir-s_Vault.git
cd "Mimir-s_Vault"

# Create virtual environment & install dependencies
python3 -m venv .venv
.venv/bin/pip install "fastmcp>=3.4.0" "mcp>=1.2.0" "pydantic>=2.0.0"

2. Verify Installation & Test Graph Engine

.venv/bin/python test_graph.py

Expected Result: ALL TESTS PASSED SUCCESSFULLY!

MCP Client Setup

Add Mimirs_Vault to your preferred AI Client configuration:

Google Antigravity IDE (agy.json / Settings) or Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "Mimirs_Vault": {
      "command": "<path-to-repo>/.venv/bin/python",
      "args": [
        "<path-to-repo>/main.py"
      ]
    }
  }
}

Note: Replace <path-to-repo> with the absolute path where you cloned Mimir-s_Vault (e.g. /home/user/projects/Mimir-s_Vault or C:/Projects/Mimir-s_Vault).

Cursor IDE

1. Open Cursor Settings → Features → MCP Servers.

2. Click + Add New MCP Server.

3. Name: Mimirs_Vault

4. Type: command

5. Command: <path-to-repo>/.venv/bin/python "<path-to-repo>/main.py"

MCP Tool Reference

Mimirs_Vault exposes 7 core tools for AI agent navigation:

System Prompts & Resources

MCP Prompts

• memory_first_workflow: Instructs AI agents: "Consult get_root_node first. Read ONLY the target source files mapped in module wikilinks."

• bootstrap_project_context: Guides AI to auto-scan an un-documented repository and build .context/ notes.

MCP Resources

• context://root — Direct read of .context/overview.md.

• context://decisions — Direct read of .context/decisions.md.

Agent Workflow Guide

1. Bootstrapping a New Repository

In any project workspace, prompt your AI agent:

"Run the bootstrap_project_context prompt to initialize the memory graph for this repository."

The AI will call init_context_graph and create_module_node to build your project's .context/ tree.

2. Daily Task Execution

When asking your AI agent to implement a feature:

"Implement user authentication with JWT. Check the memory graph first."

The AI will:

1. Call get_root_node to inspect .context/overview.md.

2. Follow [[modules/auth]] to extract mapped file paths (src/auth/service.py).

3. Inspect & edit only src/auth/service.py (zero token waste).

3. Logging Architecture Decisions

"Log an architectural decision that we switched to RS256 JWT signing."

The AI calls log_decision, appending ADR-002 to .context/decisions.md.

Visualizing Your Memory Graph in 3D

Because all nodes use standard Obsidian Wikilink syntax ([[modules/auth]]), open your repository's .context/ directory in:

• Obsidian

• VS Code Foam Extension

Enjoy an interactive, 3D visual graph of your codebase's architectural memory!

ᛗ Built with Wisdom for AI-First Engineering ᛗ

Crafted with Python FastMCP • Report Issue • Submit Request