Skip to main content
Glama

msf_process_start

Destructive

Starts a local executable with literal argv and no shell, returning a process_id for interactive terminal input/output or exact binary output via process controls.

Instructions

Start a local executable with literal argv, without a shell.

Use ["msfconsole", "-q"] with terminal=true for a real interactive PTY, including IRB, prompts, and terminal input. Use ["msfvenom", "--help"] with terminal=false for exact binary output and separate stderr. Other installed Framework utilities and interpreters can be run the same way. These processes do not share the RPC daemon's in-memory sessions or jobs. Returns immediately with process_id. Read output, write input, signal, resize, and close using the process tools. cwd and env are optional.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "argv": "<argv>"
    },
    "name": "msf_process_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
cwdNo
envNo
argvYes
rowsNo
columnsNo
terminalNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already flag destructive/openWorld/non-idempotent, so the description's added value is async behavior ('Returns immediately with process_id'), the lifecycle handoff to the process_* tools, and the isolation note about not sharing daemon sessions/jobs. It does not state the privilege context the child executable inherits or failure behavior, which would matter for arbitrary local execution.

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

Conciseness4/5

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

Front-loaded with the core verb and the no-shell constraint, then the highest-value usage distinction. Line breaks split sentences mid-clause and the closing 'cwd and env are optional' is a weak trailing afterthought, but overall it is dense with no filler.

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

Completeness3/5

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

An output schema exists, so return values need only the 'returns process_id' note, which it provides. However, for a six-parameter tool with zero schema descriptions, the description leaves rows/columns unexplained and does not say whether env replaces or merges with the inherited environment — both needed to call it correctly.

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

Parameters3/5

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

With 0% schema description coverage the description must carry all six parameters. It meaningfully defines argv (literal argv, no shell), terminal (with scenario examples), and touches cwd/env only as 'optional', while rows and columns — the PTY dimensions — get no mention at all despite being tied to the terminal=true path.

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 and resource ('Start a local executable with literal argv, without a shell') and immediately clarifies scope relative to siblings: it is not a console/RPC session ('These processes do not share the RPC daemon's in-memory sessions or jobs'). An agent can distinguish this from msf_console_create and msf_rpc without opening either schema.

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 concrete, actionable routing with parameter values — ['msfconsole','-q'] with terminal=true for interactive PTY/IRB, ['msfvenom','--help'] with terminal=false for exact binary output — and notes other utilities work the same way. It never explicitly names msf_console_create as the alternative when a shared daemon session is wanted, which is the one obvious omission.

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