issue-close

Closes an issue with an optional comment and reason. Returns structured data with issue number, state, URL, reason, and comment URL.

SERVERSearch SOURCEDave-London/Pare

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-dave-london-pare-search/issue-close.md

WHAT IT DOES

What issue-close does on Search

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

RISK

Why issue-close is rated Medium

Closing an issue is a write operation that modifies the issue's state. While state changes are typically reversible (issues can be reopened), this represents a significant modification to data that could affect workflows and visibility. It's not Destructive because closing is reversible; it's not Read because it has side effects; it's not Execute/Financial/Other.

From the tool's definition Tool description states it 'Closes an issue' which is an irreversible state change to an issue object. However, the description does not indicate deletion of data, only a state transition (closing).

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs issue-close safely

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

issue-close Rate-limited

issue-close 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": {
    "issue-close": {
      "limits": [
        {
          "counter": "issue-close_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 Search, apply this rule, and every issue-close call is checked against it from then on.

FAQ

Questions about issue-close

What does the issue-close tool do? +

Closes an issue with an optional comment and reason. Returns structured data with issue number, state, URL, reason, and comment URL. It is categorised as a Write tool in the Search MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on issue-close? +

Register the Search MCP server in PolicyLayer and add a rule for issue-close: 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 Search. Nothing to install.

What risk level is issue-close? +

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

Can I rate-limit issue-close? +

Yes. Add a rate_limit block to the issue-close 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 issue-close completely? +

Set action: deny in the PolicyLayer policy for issue-close. 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 issue-close? +

issue-close is provided by the Search MCP server (Dave-London/Pare). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Search, and thousands of servers like it.

This server

All 202 Search tools →

Across the catalogue

The MCP Attack Database →

Guides

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