copypass_run

SERVERUnClick SOURCE@unclick/mcp-server

High RISK CLASS

Category Execute

Parameters 80 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-malamutemayhem-unclick-mcp-server/copypass-run.md

WHAT IT DOES

What copypass_run does on UnClick

AI agents invoke copypass_run to trigger actions in UnClick. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

Parameter	Type	Required	Description
`goal`	string	—	Optional goal for the copy, such as clarity, conversion, or trust.
`channel`	string	—	Optional surface label such as homepage_hero, pricing_section, or onboarding_email.
`profile`	string	—	Review depth label for this scoped run. Defaults to smoke.
`audience`	string	—	Optional intended audience for the copy.
`copy_text`	string	—	The AI-generated copy to review. Optional when copyroom_source_packet is provided; exact-copy verification compares this text byte-for-byte against the packet.
`copyroom_required`	boolean	—	Set true when exact fidelity matters. Missing copyroom_source_packet returns COPYROOM_MISSING instead of a run with a null receipt.
`copyroom_source_packet`	object	—	Exact source packet for CopyRoom fidelity work. Use this instead of retyping source text when code, prompts, labels, tables, documents, or user-provided text mu
`copyroom_output_pointer`	string	—	Pointer to the intended output artifact for the CopyRoom receipt.

Parameters from the server's own tool schema.

RISK

Why copypass_run is rated High

The tool initiates an external review process (CopyPass) against caller-supplied AI-generated copy, producing structured artifacts and receipts. This is an Execute-category action because it runs an external operation whose outputs depend on the arguments provided. It is not purely Read (it processes and generates artifacts), not Write (no persistent data creation described), and not Destructive or Financial.

From the tool's definition 'Start a deterministic CopyPass review' and 'Returns evidence-backed copy findings... structured copypass_receipt_v1 proof envelope' — triggers an external review/processing operation on caller-provided content

Risk signalsHigh parameter count (13 properties)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs copypass_run safely

PolicyLayer is an MCP gateway: it sits between your AI agents and UnClick, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For copypass_run, this is the rule to start with:

copypass_run Rate-limited

copypass_run stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "copypass_run": {
      "limits": [
        {
          "counter": "copypass_run_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect UnClick, apply this rule, and every copypass_run call is checked against it from then on.

FAQ

Questions about copypass_run

What does the copypass_run tool do? +

Start a deterministic CopyPass review for caller-provided AI-generated copy. Returns evidence-backed copy findings, scope boundaries, disclaimer text, a structured copypass_receipt_v1 proof envelope, and optional CopyRoom exact-copy receipt. It is categorised as a Execute tool in the UnClick MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

What parameters does copypass_run accept? +

copypass_run accepts 8 parameters: goal, channel, profile, audience, copy_text, copyroom_required, copyroom_source_packet, copyroom_output_pointer. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on copypass_run? +

Register the UnClick MCP server in PolicyLayer and add a rule for copypass_run: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches UnClick. Nothing to install.

What risk level is copypass_run? +

copypass_run is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit copypass_run? +

Yes. Add a rate_limit block to the copypass_run rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block copypass_run completely? +

Set action: deny in the PolicyLayer policy for copypass_run. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides copypass_run? +

copypass_run is provided by the UnClick MCP server (@unclick/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on UnClick, and thousands of servers like it.

This server

All 1662 UnClick tools → High-risk tools on this server →

Across the catalogue

run on 0sec →shortcuts_run on Apple Apps MCP →run_emba_scan on EMBA-MCP → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →