gh_run
Run any gh (GitHub CLI) subcommand. Pass the args as a list (no leading gh). Pre-flights install + auth state, blocks credential-printing subcommands, and requires confirm:true for destructive commands such as repo delete or gh api -X DELETE.
This record as markdown: /tools/io-github-kivanccakmak-yaver/gh-run.md
What gh_run does on Yaver
AI agents invoke gh_run to trigger actions in Yaver. 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 |
|---|---|---|---|
args | array | Yes | subcommand + flags, e.g. ["repo", "view", "--json", "description"] |
confirm | boolean | — | Required for destructive commands such as `gh repo delete` or `gh api -X DELETE`. |
directory | string | — | Working directory; defaults to agent cwd |
Parameters from the server's own tool schema.
Why gh_run is rated High
This tool executes arbitrary GitHub CLI subcommands with user-controlled arguments. While it has guardrails (confirmation requirement for destructive operations, credential-printing blocks), the ability to run any gh subcommand—including API calls, workflows, deployments, and repository management—represents arbitrary code execution against external services.
From the tool's definition Run any `gh` (GitHub CLI) subcommand; requires confirm:true for destructive commands such as `repo delete` or `gh api -X DELETE`
Risk signalsAccepts file system path (directory)
Attacks that exploit this kind of access
The rule that runs gh_run safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Yaver, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For gh_run, this is the rule to start with:
gh_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.
The button opens the PolicyLayer dashboard: create your workspace, connect Yaver, apply this rule, and every gh_run call is checked against it from then on.
Questions about gh_run
Run any gh (GitHub CLI) subcommand. Pass the args as a list (no leading gh). Pre-flights install + auth state, blocks credential-printing subcommands, and requires confirm:true for destructive commands such as repo delete or gh api -X DELETE. It is categorised as a Execute tool in the Yaver MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
gh_run accepts 3 parameters: args, confirm, directory. Required: args. The full parameter table on this page comes from the server's own tool schema.
Register the Yaver MCP server in PolicyLayer and add a rule for gh_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 Yaver. Nothing to install.
gh_run is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the gh_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.
Set action: deny in the PolicyLayer policy for gh_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.
gh_run is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Yaver, and thousands of servers like it.
Across the catalogue