sloppass_run

SERVERUnClick SOURCE@unclick/mcp-server

High RISK CLASS

Category Execute

Parameters 61 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/sloppass-run.md

WHAT IT DOES

What sloppass_run does on UnClick

AI agents invoke sloppass_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
`diff`	string	—	Unified diff text to inspect. Added lines are converted into scoped file evidence.
`files`	array	—	Source files to inspect. Use this for scoped local artifacts or paste-backed code review.
`checks`	array	—	Optional SlopPass check categories to run. Defaults to all built-in categories.
`target`	object	Yes	Target being inspected. For live GitHub PR review, use kind=pr with repo plus number, or url/pr_url.
`provider`	string	—	Provider mode to record in the receipt. Defaults to http and does not call a model.
`target_sha`	string	—	Optional PR or commit SHA for receipt staleness checks.

Parameters from the server's own tool schema.

RISK

Why sloppass_run is rated High

The tool executes an analysis pipeline (SlopPass) against provided source files or fetches remote GitHub PR diffs, then generates multiple report formats. While it explicitly states it does not execute code or persist content, it does trigger external operations (fetching remote .diff files) and runs a processing engine on caller-supplied inputs.

From the tool's definition 'Run SlopPass against caller-provided source files, a unified diff, or a GitHub PR target whose public .diff should be fetched' — triggers an external analysis operation against caller-provided inputs and fetches remote content

Risk signalsAccepts file system path (files[].path) · Accepts URL/endpoint input (target.url) · Accepts raw HTML/template content (files[].content) · High parameter count (17 properties)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs sloppass_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 sloppass_run, this is the rule to start with:

sloppass_run Rate-limited

sloppass_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": {
    "sloppass_run": {
      "limits": [
        {
          "counter": "sloppass_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 sloppass_run call is checked against it from then on.

FAQ

Questions about sloppass_run

What does the sloppass_run tool do? +

Run SlopPass against caller-provided source files, a unified diff, or a GitHub PR target whose public .diff should be fetched. Returns an evidence-backed slop-signal receipt plus JSON, markdown, and HTML reports. SlopPass does not execute code, clone repositories, persist source content, or make paid model calls by default. 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 sloppass_run accept? +

sloppass_run accepts 6 parameters: diff, files, checks, target, provider, target_sha. Required: target. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on sloppass_run? +

Register the UnClick MCP server in PolicyLayer and add a rule for sloppass_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 sloppass_run? +

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

Can I rate-limit sloppass_run? +

Yes. Add a rate_limit block to the sloppass_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 sloppass_run completely? +

Set action: deny in the PolicyLayer policy for sloppass_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 sloppass_run? +

sloppass_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 →