What is the key difference between Kage and Hive?

Kage belongs to the Knowledge & Memory category with local stdio execution, while Hive belongs to the Knowledge & Memory category with local stdio execution.

How do I install Kage or Hive in Claude Desktop or Cursor?

Copy the mcpServers JSON configuration snippet provided on this page into your claude_desktop_config.json or ~/.cursor/mcp.json file and restart your AI client.

Are Kage and Hive free or paid?

Kage operates under a Free / Open Source model (No auth required). Hive operates under a Free / Open Source model (No auth required).

Which MCP server has more tools and community activity?

Kage lists 6 tools with 3 views and 32 GitHub stars. Hive lists 11 tools with 1 views and 9 GitHub stars.

Can I use both Kage and Hive together in the same MCP host?

Yes! MCP hosts like Claude Desktop, Cursor, Windsurf, Cline, and VS Code support configuring multiple servers under the mcpServers object simultaneously.

How do I install Kage or Hive in Claude Desktop, Cursor, or Windsurf?

Both servers follow the standard Model Context Protocol configuration format. Simply copy the JSON block from the configuration section above and paste it into your AI client's mcpServers configuration object (for instance in claude_desktop_config.json or ~/.cursor/mcp.json ), then completely restart or refresh the application.

Are Kage and Hive free to use, or do they require API keys?

Kage is listed under a Free / Open Source model with No auth required . Hive operates under a Free / Open Source model with No auth required . If environment variables are required (such as API keys), be sure to define them under the env key in your MCP client's configuration file.

Can I run both Kage and Hive at the same time in my AI client?

Yes! MCP clients support multi-server orchestration. You can include both kage-core-kage and mlorentedev-hive as distinct keys inside the single mcpServers object in your configuration file. Your AI assistant will automatically select and call the appropriate tool from either server during chat sessions.

Which MCP server has higher directory engagement and quality ratings?

On AllMCPs, Kage has a Quality Score of 61 /100 ( Good ) with 3 views, 0 installs, and 32 GitHub stars. Hive holds a Quality Score of 60 /100 ( Good ) with 1 views, 0 installs, and 9 GitHub stars.

Side-by-Side Model Context Protocol Comparison

Kage vs Hive

In-depth architectural comparison of the Kage and Hive 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.

At a Glance & Executive Verdict

Kage

Knowledge & Memory · Local stdio

Quality: 61/100 (Good) | Auth: No auth required

Hive

Knowledge & Memory · Local stdio

Quality: 60/100 (Good) | Auth: No auth required

Verdict Summary: Choose Kage if you need specialized Knowledge & Memory tools running via a local process. Choose Hive if your workspace requires Knowledge & Memory integration with local subprocess execution. Both servers can be configured concurrently in your client's mcpServers manifest.

Which MCP Server Should You Choose?

Choose Kage 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: Git-native memory packets, Open Knowledge Format bundles, Deterministic citation verification.

Explore Kage Details

Choose Hive 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).
You have access to required keys: VAULT_PATH, HIVE_VAULT_PATH, OPENROUTER_API_KEY.
Primary tools included: vault_query, vault_search, vault_list.

Explore Hive Details

Feature & Specification Comparison

Specification	Kage kage-core Knowledge & Memory	Hive mlorentedev Knowledge & Memory
Summary	Verified, git-native memory for coding agents. Memory is plain JSON packets committed in your repo, each checked against the code it cites — hallucinated citations rejected at write, stale or changed memory withheld at recall, plus diff-time stale-catch. Local-only (BM25 + vectors), no account, no API key. npx -y @kage-core/kage-graph-mcp install	On-demand Obsidian vault access via MCP. Adaptive context loading (67-82% token savings), full-text and ranked search, health checks, auto git commit, and worker delegation to cheaper models. 10 tools, works with any MCP client.
Category & Scope

Tools & Capabilities Breakdown

Kage Tools (6)

Git-native memory packets

Open Knowledge Format bundles

Deterministic citation verification

Stale-memory detection and withholding

Local BM25 and vector search

Agent wiring and MCP configuration

Hive Tools (11)

vault_query

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).

Kage Configuration

mcpServers (Claude Desktop / Cursor)

{
  "mcpServers": {
    "kage-core-kage": {
      "command": "npx",
      "args": [
        "-y",
        "@kage-core/kage-graph-mcp",
        "install"
      ]
    }
  }
}

Hive Configuration

mcpServers (Claude Desktop / Cursor)

{
  "mcpServers": {
    "mlorentedev-hive": {
      "command": "uvx",
      "args": [
        "--upgrade"
      ],
      "env": {
        "VAULT_PATH": "YOUR_VAULT_PATH_HERE",
        "HIVE_VAULT_PATH": "YOUR_HIVE_VAULT_PATH_HERE",
        "OPENROUTER_API_KEY": "YOUR_OPENROUTER_API_KEY_HERE"
      }
    }
  }
}

Frequently Asked Questions

Kage is categorized under Knowledge & Memory and uses a local stdio subprocess. In contrast, Hive belongs to Knowledge & Memory using local stdio subprocess. Select Kage when you need capabilities focused on knowledge & memory and Hive when you require tools for knowledge & memory.

More alternatives to Kage More alternatives to Hive Knowledge & Memory category hub