open-edison 0.1.16

Open-source MCP security, aggregation, and monitoring. Single-user, self-hosted MCP proxy.

OpenEdison

Open-source MCP security gateway that prevents data exfiltration—via direct access or tool chaining—with full monitoring for local single‑user deployments. Provides core functionality of https://edison.watch for local, single-user use.

Just want to run it?

curl -fsSL https://raw.githubusercontent.com/Edison-Watch/open-edison/main/curl_pipe_bash.sh | bash

Run locally with uvx: uvx open-edison --config-dir ~/edison-config

📧 Interested in connecting AI to your business software with proper access controls? Contact us to discuss.

Features

• Single-user MCP proxy - No multi-user complexity, just a simple proxy for your MCP servers
• JSON configuration - Easy to configure and manage your MCP servers
• Simple local frontend - Track and monitor your MCP interactions, servers, and sessions.
• Session tracking - Track and monitor your MCP interactions
• Simple API - REST API for managing MCP servers and proxying requests
• Docker support - Run in a container for easy deployment

Quick Start

Install from PyPI

Prerequisites

• Pipx/uvx

# Using uvx
uvx open-edison --help

# Using pipx
pipx install open-edison
open-edison --help

Run with a custom config directory:

open-edison run --config-dir ~/edison-config
# or via environment variable
OPEN_EDISON_CONFIG_DIR=~/edison-config open-edison run

Run with Docker

There is a dockerfile for simple local setup.

# Single-line:
git clone https://github.com/GatlingX/open-edison.git && cd open-edison && make docker_run

# Or
# Clone repo
git clone https://github.com/GatlingX/open-edison.git
# Enter repo
cd open-edison
# Build and run
make docker_run

The MCP server will be available at http://localhost:3000 and the api + frontend at http://localhost:3001.

Run from source

1. Clone the repository:

git clone https://github.com/GatlingX/open-edison.git
cd open-edison

1. Set up the project:

make setup

1. Edit config.json to configure your MCP servers. See the full file: config.json, it looks like:

{
  "server": { "host": "0.0.0.0", "port": 3000, "api_key": "..." },
  "logging": { "level": "INFO", "database_path": "sessions.db" },
  "mcp_servers": [
    { "name": "filesystem", "command": "npx", "args": ["-y", "@modelcontextprotocol/server-filesystem", "/tmp"], "enabled": true },
    { "name": "github", "enabled": false, "env": { "GITHUB_PERSONAL_ACCESS_TOKEN": "..." } }
  ]
}

1. Run the server:

make run
# or, from the installed package
open-edison run

The server will be available at http://localhost:3000.

MCP Connection

Connect any MCP client to Open Edison:

npx -y mcp-remote http://localhost:3000/mcp/ --http-only --header "Authorization: Bearer your-api-key"

Or add to your MCP client config:

{
  "mcpServers": {
    "open-edison": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "http://localhost:3000/mcp/", "--http-only", "--header", "Authorization: Bearer your-api-key"]
    }
  }
}

Usage

API Endpoints

See API Reference for full API documentation.

Development

Setup

Setup from source as above.

Run

Server doesn't have any auto-reload at the moment, so you'll need to run & ctrl-c this during development.

make run

Tests/code quality

We expect make ci to return cleanly.

make ci

Configuration

The config.json file contains all configuration:

• server.host - Server host (default: localhost)
• server.port - Server port (default: 3000)
• server.api_key - API key for authentication
• logging.level - Log level (DEBUG, INFO, WARNING, ERROR)
• mcp_servers - Array of MCP server configurations

Each MCP server configuration includes:

• name - Unique name for the server
• command - Command to run the MCP server
• args - Arguments for the command
• env - Environment variables (optional)
• enabled - Whether to auto-start this server

Security & Permissions System

Open Edison includes a comprehensive security monitoring system that tracks the "lethal trifecta" of AI agent risks:

1. Private data access - Access to sensitive local files/data
2. Untrusted content exposure - Exposure to external/web content
3. External communication - Ability to write/send data externally

The configuration allows you to classify these risks across tools, resources, and prompts using separate configuration files.

In addition to trifecta, we track Access Control Level (ACL) for each tool call, that is, each tool has an ACL level (one of PUBLIC, PRIVATE, or SECRET), and we track the highest ACL level for each session. If a write operation is attempted to a lower ACL level, it is blocked.

Tool Permissions (tool_permissions.json)

Defines security classifications for MCP tools. See full file: tool_permissions.json, it looks like:

{
  "_metadata": { "last_updated": "2025-08-07" },
  "builtin": {
    "get_security_status": { "enabled": true, "write_operation": false, "read_private_data": false, "read_untrusted_public_data": false, "acl": "PUBLIC" }
  },
  "filesystem": {
    "read_file": { "enabled": true, "write_operation": false, "read_private_data": true, "read_untrusted_public_data": false, "acl": "PRIVATE" },
    "write_file": { "enabled": true, "write_operation": true, "read_private_data": true, "read_untrusted_public_data": false, "acl": "PRIVATE" }
  }
}

Resource Permissions (resource_permissions.json)

Defines security classifications for resource access patterns. See full file: resource_permissions.json, it looks like:

{
  "_metadata": { "last_updated": "2025-08-07" },
  "builtin": { "config://app": { "enabled": true, "write_operation": false, "read_private_data": false, "read_untrusted_public_data": false } }
}

Prompt Permissions (prompt_permissions.json)

Defines security classifications for prompt types. See full file: prompt_permissions.json, it looks like:

{
  "_metadata": { "last_updated": "2025-08-07" },
  "builtin": { "summarize_text": { "enabled": true, "write_operation": false, "read_private_data": false, "read_untrusted_public_data": false } }
}

Wildcard Patterns

All permission types support wildcard patterns:

• Tools: server_name/* (e.g., filesystem/* matches all filesystem tools)
• Resources: scheme:* (e.g., file:* matches all file resources)
• Prompts: type:* (e.g., template:* matches all template prompts)

Security Monitoring

All items must be explicitly configured - unknown tools/resources/prompts will be rejected for security.

Use the get_security_status tool to monitor your session's current risk level and see which capabilities have been accessed. When the lethal trifecta is achieved (all three risk flags set), further potentially dangerous operations are blocked.

Documentation

📚 Complete documentation available in docs/

• Getting Started - Quick setup guide
• Configuration - Complete configuration reference
• API Reference - REST API documentation
• Development Guide - Contributing and development

License

GPL-3.0 License - see LICENSE for details.