Atlas / MCP servers / ooples / Console Automation

Console AutomationBLOCK

Name: Console Automation
Author: ooples

mcp/ooples/console-automation

MCP server by ooples · Audited 2026-10-08

⚑ Report / re-scan Source ↗

MCP server for AI-driven console application automation and monitoring

Verdict

BLOCK

Grade

Trust score

44 /100

Exposed tools

54 38r · 12w · 4d

Transport

stdio

License

MIT

Stars

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

Model Context Protocol (MCP) server for controlled interaction with local console applications and remote SSH sessions, including output monitoring, error detection, and long-running workflows.

[](https://github.com/ooples/mcp-console-automation) [](LICENSE) [](https://nodejs.org)

Security status

This server can execute arbitrary commands and open remote SSH sessions. Treat it like a privileged terminal, not a low-risk documentation connector:

keep MCP tool approvals enabled for command/session mutations;
prefer SSH keys or environment-variable credential references over inline secrets;
use a restricted deployment account and a separate production approval step;
leave MCP_DEBUG_LOG and MCP_LOG_DIR unset unless diagnostics are explicitly required;
leave session persistence disabled unless recovery metadata is explicitly required;
install cloud, container, and serial integrations only when needed.

Features

🚀 Core Capabilities

Full Terminal Control: Create and manage up to 50 concurrent console sessions
Multi-Protocol Support: Local shells (cmd, PowerShell, pwsh, bash, zsh, sh) and remote SSH connections
Interactive Input: Send text input and special key sequences (Enter, Tab, Ctrl+C, etc.)
Real-time Output Monitoring: Capture, filter, and analyze console output with advanced search
Streaming Support: Efficient streaming for long-running processes with pattern matching
Automatic Error Detection: Built-in patterns to detect errors, exceptions, and stack traces across languages
Cross-platform: Works on Windows, macOS, and Linux without native dependencies

🔐 SSH & Remote Connections

Full SSH Support: Password and key-based authentication with passphrase support

Read from source at commit a3b00c36df3eOBSERVED · 2026-10-08

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code

claude mcp add console-automation-mcp --env AUDIT_ENCRYPTION_KEY=${AUDIT_ENCRYPTION_KEY} --env AZURE_CLIENT_SECRET=${AZURE_CLIENT_SECRET} --env AZURE_KEY_VAULT_URL=${AZURE_KEY_VAULT_URL} --env AZURE_SECRET_NAME=${AZURE_SECRET_NAME} -- npx -y [email protected]

claude-desktop

{
  "mcpServers": {
    "console-automation-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "AUDIT_ENCRYPTION_KEY": "${AUDIT_ENCRYPTION_KEY}",
        "AZURE_CLIENT_SECRET": "${AZURE_CLIENT_SECRET}",
        "AZURE_KEY_VAULT_URL": "${AZURE_KEY_VAULT_URL}",
        "AZURE_SECRET_NAME": "${AZURE_SECRET_NAME}"
      }
    }
  }
}

Exposed tools (54)

38 read · 12 write · 4 destructive. Blast radius: 4 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.

Tool	Risk	Description
`check_ssh_connectivity`	read	Verify SSH service availability and network connectivity
`cleanup_resources`	read	Clean up unused resources
`console_assert_exit_code`	read	Assert that session exit code matches expected value
`console_assert_no_errors`	read	Assert that session output contains no error messages
`console_assert_output`	read	Assert that session output matches expected criteria
`console_assert_state`	read	Assert that session state matches expected values
`console_cancel_job`	read	Cancel a running background job
`console_cleanup_jobs`	read	Clean up completed background jobs
`console_cleanup_sessions`	read	Clean up inactive or stuck sessions
`console_clear_output`	destructive	Clear the output buffer for a session
`console_compare_snapshots`	read	Compare two session snapshots and show differences
`console_create_session`	write	Create a new console session for running a command
`console_detect_errors`	read	Analyze console output for errors and exceptions
`console_execute_async`	write	Execute a command in background (async mode)
`console_execute_command`	write	Execute a command in an existing session or create a new one-off session
`console_get_alerts`	read	Get current monitoring alerts including performance, error, security, and anomaly alerts
`console_get_command_history`	read	Get the command execution history for a session
`console_get_job_metrics`	read	Get metrics and statistics about background job execution
`console_get_job_output`	read	Get output from a background job
`console_get_job_progress`	read	Get progress information for a background job
`console_get_job_result`	read	Get the complete result of a background job
`console_get_job_status`	read	Get the status of a background job
`console_get_monitoring_dashboard`	read	Get real-time monitoring dashboard data with metrics, alerts, and system status
`console_get_output`	read	Get output from a console session with server-side filtering, pagination, and search capabilities
`console_get_resource_usage`	read	Get resource usage statistics for all sessions
`console_get_session_metrics`	read	Get detailed metrics for a specific console session
`console_get_session_state`	read	Get the execution state of a console session
`console_get_stream`	read	Get streaming output from a long-running console session
`console_get_system_metrics`	read	Get comprehensive system monitoring metrics including CPU, memory, disk, and network usage
`console_list_jobs`	read	List background jobs for a session or all sessions
`console_list_profiles`	read	List all saved connection and application profiles
`console_list_sessions`	read	List all active console sessions
`console_remove_profile`	destructive	Remove a saved profile
`console_save_profile`	write	Save a connection or application profile for reuse
`console_save_snapshot`	write	Save a snapshot of current session state
`console_send_input`	write	Send text input to a console session
`console_send_key`	write	Send special key sequences to a console session
`console_start_monitoring`	write	Start monitoring for a specific session with custom monitoring options
`console_stop_monitoring`	write	Stop monitoring for a specific session
`console_stop_session`	write	Stop a console session
`console_use_profile`	write	Create a session using a saved profile
`console_wait_for_output`	read	Wait for specific output pattern in console
`flush_dns`	destructive	Clear DNS cache
`minimal_mode`	read	Switch to minimal resource mode
`network_degradation`	read	Switch to degraded network mode
`ping_host`	read	Test network connectivity to target host
`prompt_reauth`	read	Prompt for re-authentication
`recreate_ssh_connection`	write	Create new SSH connection with fresh authentication
`reduce_memory_usage`	read	Reduce memory consumption
`refresh_credentials`	read	Attempt credential refresh
`reset_network_stack`	destructive	Reset network connection
`retry_ssh_connection`	read	Retry SSH connection with same credentials
`ssh_degraded_mode`	read	Switch to SSH degraded mode with increased timeouts
`us-central1-a`	read	us-central1-a

Trust audit

BLOCKgrade F · trust 44/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.

Layer	What it checks	Result
L0	Provenance & inventory	PASS
L1	Static analysis of the code	FAIL
L2	Instruction surface (what it tells the agent)	PASS
L3	Class-specific surface	WARN
L4	Behavioural (sandbox)	SKIPPED

What the source does

Filesystem: declared (10 observation(s))
Network: declared (8 observation(s))
Shell: declared (9 observation(s))
Dependencies: not all pinned
Secrets in source: found

Findings (25)

HIGHCode injection · code.deserialize · CWE-78, CWE-94, CWE-95

src/protocols/AnsibleProtocol.ts:491

yaml.load(content);

Why it matters. deserialises untrusted bytes into live objects

Fix. use json or yaml.safe_load

HIGHCode injection · code.deserialize · CWE-78, CWE-94, CWE-95

src/protocols/AnsibleProtocol.ts:677

inventory = { ...inventory, ...(yaml.load(content) as any) };

Why it matters. deserialises untrusted bytes into live objects

Fix. use json or yaml.safe_load

HIGHCode injection · code.deserialize · CWE-78, CWE-94, CWE-95

src/protocols/KubernetesProtocol.ts:271

const config = yaml.load(this.connectionOptions.kubeconfig) as any;

Why it matters. deserialises untrusted bytes into live objects

Fix. use json or yaml.safe_load

HIGHCode injection · code.deserialize · CWE-78, CWE-94, CWE-95

src/testing/TestDataLoader.ts:180

return yaml.load(content);

Why it matters. deserialises untrusted bytes into live objects

Fix. use json or yaml.safe_load