Cybersec Toolkit

Overview Schema Source Related Servers Discussions Admin

run_tool

Destructive

Execute installed cybersecurity tools or system utilities and return output with sanitized arguments, timeout control, and truncation. Run locally or on remote hosts via SSH.

Instructions

Execute an installed cybersecurity tool or system utility and return its output.

Runs tools from the 670+ registry as well as ~120 standard system utilities (strings, file, curl, grep, base64, xxd, jq, etc.) that are allowed without being in the registry. Arguments are sanitized to prevent shell injection. Timeout is clamped to 1-300s. Output is truncated at 200KB.

Network tools (including curl, wget, ping, etc.) are restricted to local/private targets by default. Set CYBERSEC_MCP_ALLOW_EXTERNAL=1 to allow external targets.

When host is provided, the tool is executed on the remote host via SSH. The tool does not need to be installed locally — only on the remote host.

Input Schema

TableJSON Schema

Name	Required	Description
`args`	No	Command-line arguments as a string (e.g. "--version" or "-sV 10.0.0.1").
`host`	No	Optional remote host name (as configured via manage_remote_hosts).
`timeout`	No	Maximum execution time in seconds (default 120, max 300).
`tool_name`	Yes	Name of the tool to run (registry tool or system utility).

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.2.0Sep 9, 2026

TDQS

A4.7/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare destructive/openWorld/non-idempotent, and the description adds substantial context on top: argument sanitization against shell injection, timeout clamping to 1-300s, 200KB output truncation, default local/private network restriction with an env-var escape hatch, and SSH semantics where the tool need only exist on the remote host.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action, then layered constraints in short, well-separated paragraphs. Every sentence carries operational information (sanitization, timeout clamp, truncation, network policy, SSH) with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Complete for a high-risk execution tool: safety profile is covered by annotations, argument and host semantics by the description, and return values by the existing output schema. An agent has everything needed to call it correctly and safely.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning for 'host' (executed remotely via SSH, tool need not be installed locally) and for 'args' (sanitized to prevent shell injection). Timeout and tool_name semantics are largely left to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Execute') and resource ('an installed cybersecurity tool or system utility') plus the outcome ('return its output'). It clearly separates itself from siblings like run_script and run_pipeline by scoping to registry tools and a fixed set of allowed system utilities.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives rich context: registry vs. ~120 built-in system utilities, network tools restricted to local/private targets unless CYBERSEC_MCP_ALLOW_EXTERNAL=1, and remote execution when host is supplied. It never explicitly says when to prefer run_script/run_pipeline or the suggest/recommend siblings, so routing is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server