G

Granum

Verified Integration
Author: @e-reitbauerCategory: ServerApplication
JSON-RPC 2.0
Protocol Standard
Sub-second
Execution Latency
Active
Operational Status

Client Configuration

— Connect Granum to Claude Desktop or Cursor in seconds
{
  "mcpServers": {
    "granum": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-granum"
      ],
      "env": {}
    }
  }
}
Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).
Architecture & Capabilities

System Overview

Manages persistent semantic memory for AI agents like Claude Code using a local vector and graph database.

Indexed Date

7/23/2026

License

Open Source

Protocol Layer

stdio / SSE RPC

Frequently Asked Questions

Architecture and operational details for Granum

Yes, Granum's memory is persistent across sessions, branch switches, and compaction. It's stored in a local Kuzu database and exported to `.granum/chunks.ndjson` for Git portability, enabling line-level diffs and clean merges. Memory is also branch-isolated.

Related MCP Servers

Browse all servers →
C
@carboneio
Carbone

Empower AI assistants to generate and convert documents, manage templates, and automate document workflows efficiently.

ClaudeSearchDatabase+65 FAQs
Learn more
C
@sebastienrousseau
CloudCDN

Provides a multi-tenant, AI-native Content Delivery Network deployable on Cloudflare, featuring sub-100ms TTFB, AI agent controllability, and comprehensive accessibility.

ClaudeSearchDatabase+65 FAQs
Learn more

Deploy a Model Context Protocol server on Cloudflare Workers without requiring authentication.

ClaudeSearchDatabase+55 FAQs
Learn more