Synchronize repository: pull from remote, then push local changes
AI agents invoke git-sync to trigger actions in GitHub MCP Server. 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.
git-sync performs both a pull (fetching and merging remote changes) and a push (sending local changes to remote). This triggers external operations on a remote repository with effects that depend on the current state of branches and commits. While a push can be reversed by force-pushing, the act of pushing to a shared remote has broad impact on other collaborators.
From the tool's definition Synchronize repository: pull from remote, then push local changes
Attacks that exploit this kind of access
Synchronize repository: pull from remote, then push local changes. It is categorised as a Execute tool in the GitHub MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the GitHub MCP Server MCP server in PolicyLayer and add a rule for git-sync: 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-sync 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 git-sync 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-sync. 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-sync 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 →