Shadowgraph vs Plur

In-depth architectural comparison of the Shadowgraph and Plur 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 Shadowgraph 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).

Explore Shadowgraph Details

P

Choose Plur 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: plur_learn, plur_learn_batch, plur_recall.

Explore Plur Details

Feature & Specification Comparison

Specification	Shadowgraph LiLara-AI Knowledge & Memory	P Plur Knowledge & Memory
Summary	Technical Preview / Early Access. Local-first decision memory for AI agents that stores choices, rejected alternatives and their reasons, failed attempts, outcomes, provenance, and caller-invoked review conditions in a local file. Stdio MCP server; install from GitHub with Node.js 20+.	Open, local-first engram memory for AI agents: read, correct, delete; shared over MCP.
Category & Scope	Knowledge & Memory

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": {
    "lilara-ai-shadowgraph": {
      "command": "npx",
      "args": [
        "-y",
        "lilara-ai-shadowgraph"
      ]
    }
  }
}

{
  "mcpServers": {
    "plur": {
      "command": "npx",
      "args": [
        "-y",
        "@plur-ai/mcp"
      ]
    }
  }
}

Related MCP Server Comparisons