Stashes current changes
AI agents use git-stash to create or update resources in GitHub MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GitHub MCP Server environment.
git-stash temporarily saves uncommitted changes, which is a reversible modification operation (stashed changes can be retrieved via git-stash pop/apply). This is Write category (creates/modifies data reversibly) rather than Destructive because stashing is not irreversible—the stashed data persists and can be restored.
From the tool's definition Tool name 'git-stash' and description 'Stashes current changes' indicates the tool saves/modifies working directory state by storing uncommitted changes in Git's stash storage.
Attacks that exploit this kind of access
Stashes current changes. It is categorised as a Write tool in the GitHub MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the GitHub MCP Server MCP server in PolicyLayer and add a rule for git-stash: 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 GitHub MCP Server. Nothing to install.
git-stash is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the git-stash 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 git-stash. 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.
git-stash is provided by the GitHub MCP Server MCP server (jungchihoon/github-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →