Agent-Fusion vs filesystem

Side-by-side comparison to help you pick between these two MCP servers.

	Agent-Fusion by krokozyab	filesystem by modelcontextprotocol
Stars	★ 66	★ 85,748
30d uses	—	—
Score	46	77
Official	—	✓
Categories	AI / LLM ToolsDeveloper ToolsFile SystemSearch	File SystemDeveloper ToolsProductivity
Language	Kotlin	TypeScript
Last commit	1 mo ago	this month

Agent-Fusion · Summary

Local RAG semantic search engine providing AI agents access to code, documentation and PDFs via MCP protocol.

filesystem · Summary

A feature-rich MCP server for filesystem operations with dynamic directory access control.

Agent-Fusion · Use cases

Enhancing AI coding assistants with context-aware codebase exploration
Enabling document analysis and search across various file formats
Facilitating multi-agent collaboration for complex development tasks

filesystem · Use cases

Enable AI models to read and write project files during development
Allow Claude or other MCP clients to browse and analyze codebases
Provide secure sandboxed access to specific directories for content generation

Agent-Fusion · Install

Installation

Agent Fusion runs as a single JAR file with a TOML configuration file:

Download the latest JAR from the [releases page](https://github.com/krokozyab/Agent-Fusion/releases)
Create a fusionagent.toml configuration file
Run the JAR with Java: java -jar agent-fusion.jar

Claude Desktop Configuration

Add to your Claude Desktop configuration:

{
  "mcpServers": {
    "agent-fusion": {
      "command": "java",
      "args": ["-jar", "/path/to/agent-fusion.jar"],
      "env": {}
    }
  }
}

The Context Engine will be available through the query_context tool.

filesystem · Install

Installation

Using NPX

{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "/path/to/allowed/directory"
      ]
    }
  }
}

Using Docker

{
  "mcpServers": {
    "filesystem": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "--mount", "type=bind,src=/path/to/allowed/dir,dst=/projects/allowed/dir",
        "mcp/filesystem",
        "/projects"
      ]
    }
  }
}

VS Code Extension

Click the installation buttons in the README to install directly in VS Code.

Comparison generated from public README + GitHub signals. Last updated automatically.