What is parallels-ras?

A guide and REST client for Parallels Remote Application Server, a system that publishes remote desktops and applications to users. It can inspect and explain farms, sites, gateways, brokers, hosts, sessions, policies, and settings, with write operations restricted by configuration.

Use it to query RAS environments, troubleshoot connections and resource placement, look up Parallels documentation, and discover supported write operations when enabled.

It gives developers a way to investigate and manage this remote-access infrastructure without needing the repository's separate MCP client.

How RMITBLOG/ParallelsRAS_MCP configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to RMITBLOG/ParallelsRAS_MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/RMITBLOG/ParallelsRAS_MCP/main/.agents/skills/parallels-ras/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/RMITBLOG/ParallelsRAS_MCP

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rmitblog/parallelsras_mcp/parallels-ras/github.svg)](https://agentmods.dev/skills/rmitblog/parallelsras_mcp/parallels-ras)

Your own site

<a href="https://agentmods.dev/skills/rmitblog/parallelsras_mcp/parallels-ras"><img src="https://agentmods.dev/badge/skills/rmitblog/parallelsras_mcp/parallels-ras/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/rmitblog/parallelsras_mcp/parallels-ras"><img src="https://agentmods.dev/badge/skills/rmitblog/parallelsras_mcp/parallels-ras.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,076 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00057	$0.01076
Opus 5.5	$0.00023	$0.00430
Sonnet 5.5	$0.00011	$0.00215
Haiku 4.5	$0.00006	$0.00108

Measured 29d ago against content hash 55bfbd9baf01, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

parallels-ras scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 29d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/ras-query.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/parallels-ras/SKILL.md · 33 lines

How it starts

The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Parallels RAS

Parallels Remote Application Server (RAS) publishes applications and desktops from RD Session Hosts, VDI, Azure Virtual Desktop, and Remote PCs. A Farm can contain multiple Sites. Clients reach a Secure Gateway, which consults a Connection Broker for access and resource placement before connecting them to a host. Keep those roles and the Farm/Site scope distinct when interpreting API results. For the component model, common fault paths, and tool map, read RAS domain guide when the task involves diagnosis or explanation.

This skill uses a bundled local Node command to call the RAS REST API. It is an alternative to this repository's MCP server and needs no MCP client, npm installation, or source checkout. The runner exposes the same 41 RAS read queries and two Parallels documentation lookups. With RAS_ENABLE_WRITE=true, it also exposes write-operation discovery and one request tool for the documented v21.2 method/path catalog. The runner is a management client; it does not provide the separate Connection Broker API used for third-party session brokering.

Connect and discover

Use Node.js 18.14.1 or later on a machine that can reach the RAS REST API. Set RAS_HOST, RAS_USERNAME, and RAS_PASSWORD in the process environment for farm queries. Optional settings include RAS_PORT (default 20443) and RAS_IGNORE_TLS (default true). The TLS default permits common self-signed RAS deployments but disables certificate verification process-wide, including documentation lookups. Read the repository TLS guidance before using it on an untrusted network; RAS_IGNORE_TLS=false with NODE_EXTRA_CA_CERTS enables verification. Documentation lookups alone do not need RAS credentials.

Locate scripts/ras-query.mjs beside this file. Start with node <skill-directory>/scripts/ras-query.mjs list to see tool names and inputs. Use ras_farm_get_version for the REST Web Service version and ras_infra_get_sites when Site scope matters, then call only the queries relevant to the question. For example:

Read the full file on GitHub · 33 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

29d ago First seen · 33 lines · 57 tokens per session scan A 55bfbd9baf01

Subscribe to this mod's changes

parallels-ras is a skill published in the GitHub repository RMITBLOG/ParallelsRAS_MCP (3 stars, last pushed 25d ago), licensed MIT. It adds 57 tokens to every session and 1,076 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-08.

Cloud DevOps and cloud

parallels-ras next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
parallels-rasRMITBLOG/ParallelsRAS_MCP	Skill	3	25d ago	MIT	A	57	Claude Code, Codex
gke-compute-classesgoogle/skills	Skill	22k	yesterday	Apache-2.0	A	83	Claude Code, Codex
gke-reliabilitygoogle/skills	Skill	22k	yesterday	Apache-2.0	A	85	Claude Code, Codex
gke-workload-securitygoogle/skills	Skill	22k	yesterday	Apache-2.0	A	171	Claude Code, Codex
cloud-architectJeffallan/claude-skills	Skill	12k	7d ago	MIT	A	71	Claude Code
nemo-automodel-launcher-configNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	A	30	Claude Code
azure-mgmt-botservice-dotnetmicrosoft/skills	Skill	3.2k	yesterday	MIT	A	78	Claude Code

ParallelsRAS_MCP: Skill for Claude Code