Mnemostack vs Krimto

In-depth architectural comparison of the Mnemostack and Krimto MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.

Which MCP Server Should You Choose?

Choose Mnemostack when:

• You need dedicated capabilities in the Knowledge & Memory domain.
• You prefer local stdio subprocess transport architecture.
• Your security boundary fits: API Key required (BYOK (Pay Provider Direct)).
• You have access to required keys: GEMINI_API_KEY.
• Primary tools included: Hybrid vector, BM25, temporal, and graph retrieval, Reciprocal rank fusion with multi-stage reranking, Qdrant-backed persistent storage.

Explore Mnemostack Details

Choose Krimto when:

• You need dedicated capabilities in the Knowledge & Memory domain.
• You prefer local stdio subprocess transport architecture.
• Your security boundary fits: No auth required (Free / Open Source).
• Primary tools included: Markdown files stored in a user-controlled Git repository, User, team, and organization memory scopes, SQLite and sqlite-vec hybrid retrieval.

Feature & Specification Comparison

Specification	Mnemostack udjin-labs Knowledge & Memory	Krimto krimto-labs Knowledge & Memory
Summary	Durable hybrid memory for AI agents. Combines vector search, BM25, temporal retrieval, and optional Memgraph knowledge graph via reciprocal rank fusion. 6 MCP tools: health, search, answer, feedback, graphquery, graphaddtriple. Self-hosted with Qdrant backend. 82.5% strict accuracy on LoCoMo benchmark. pip install 'mnemostack[mcp]'	Open-source team memory layer for AI coding agents. Markdown files in git as storage, a user→team→org hierarchy as the access primitive, and one cross-vendor MCP server (Claude Code, Cursor, Codex, Gemini CLI). Hybrid SQLite + sqlite-vec retrieval. Apache-2.0.
Category & Scope

Tools & Capabilities Breakdown

Ready-to-Paste Client Configurations

Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).

{
  "mcpServers": {
    "udjin-labs-mnemostack": {
      "command": "uvx",
      "args": [
        "mnemostack"
      ],
      "env": {
        "GEMINI_API_KEY": "YOUR_GEMINI_API_KEY_HERE"
      }
    }
  }
}

{
  "mcpServers": {
    "krimto-labs-krimto": {
      "command": "npx",
      "args": [
        "-y",
        "@krimto-labs/krimto"
      ]
    }
  }
}

Related MCP Server Comparisons