reject_approval_request

Reject an active approval Request as the current Huly user and attach the required markdown rejection decision comment.

SERVERHuly SOURCE@firfi/huly-mcp

Medium RISK CLASS

Category Write

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-dearlordylord-huly-mcp/reject-approval-request.md

WHAT IT DOES

What reject_approval_request does on Huly

AI agents use reject_approval_request to create or update resources in Huly, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Huly environment.

RISK

Why reject_approval_request is rated Medium

This tool creates or modifies data reversibly rather than permanently destroying it. It changes the state of an approval request and adds a comment, which are write operations.

From the tool's definition Tool description states "Reject an active approval Request" - this modifies the state of an approval request object by marking it as rejected and attaching a comment.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs reject_approval_request safely

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

reject_approval_request Rate-limited

reject_approval_request stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "reject_approval_request": {
      "limits": [
        {
          "counter": "reject_approval_request_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

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

FAQ

Questions about reject_approval_request

What does the reject_approval_request tool do? +

Reject an active approval Request as the current Huly user and attach the required markdown rejection decision comment. It is categorised as a Write tool in the Huly MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on reject_approval_request? +

Register the Huly MCP server in PolicyLayer and add a rule for reject_approval_request: 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 Huly. Nothing to install.

What risk level is reject_approval_request? +

reject_approval_request is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit reject_approval_request? +

Yes. Add a rate_limit block to the reject_approval_request 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 reject_approval_request completely? +

Set action: deny in the PolicyLayer policy for reject_approval_request. 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 reject_approval_request? +

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

KEEP EXPLORING

More on Huly, and thousands of servers like it.

This server

All 518 Huly tools →

Across the catalogue

The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →