Full System Control for AI Clients
Comprehensive toolset including bash_execute, read_file, write_file, edit_file, glob, grep, prepare_upload, and prepare_download for full system control.
Stream large files via direct HTTP endpoints without context window limitations. Perfect for handling files larger than 10MB.
Granular control with read-only (ro) and read-write (rw) roles. Limit access based on client requirements.
Comprehensive JSON Lines audit trail with error details for all tool invocations. Track every action with timestamps and IP addresses.
Automatically protect MCP's own installation directory and audit logs. Prevent unauthorized access to sensitive system files.
Bearer token authentication with per-token management. Admin API for remote token management without server restarts.
pipx install algony-mymcp
Python 3.11+ required on Linux. For production use:
sudo mymcp install-service --yes sudo systemctl start mymcp
Requirements: Python 3.11+, optional ripgrep for faster grep operations.
Run the MCP server in foreground mode with temporary tokens
Install as systemd service with production configuration
Manage authentication tokens (list, add, revoke, rotate)
Print environment and dependency diagnostics
Display installed version information
Migrate from 1.x to 2.x installation format
| Tool | Permission | Description |
|---|---|---|
| bash_execute | Execute shell commands in new subprocess | |
| read_file | Read files with line numbers and pagination | |
| write_file | Create or overwrite files (up to 10MB) | |
| edit_file | Replace text in existing files precisely | |
| glob | Find files by glob pattern (max 1000 results) | |
| grep | Search file contents with regex (ripgrep support) | |
| prepare_upload | Mint signed URLs for large file uploads | |
| prepare_download | Mint signed URLs for large file downloads |
Default to read-only tokens. Grant read-write only to trusted AI clients.
Track all tool invocations with JSON Lines format including timestamps, IPs, and error details.
Automatic protection of system directories and audit logs from unauthorized access.
Prometheus metrics endpoint with optional OTLP push for observability backends.
Give your AI clients full, controlled access to Linux systems
View on GitHub