로컬 데이터를 GitHub로 푸시합니다
AI agents use sync_push to create or update resources in Remote Memory MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Remote Memory MCP Server environment.
sync_push pushes local data to a remote GitHub repository, which creates or updates data on the remote system. While the operation is reversible (via git history or further pushes), it modifies the authoritative remote state and could overwrite existing data depending on merge behavior. This is Write-category behavior.
From the tool's definition Tool description in Korean translates to 'Push local data to GitHub', and it is part of a suite that includes destructive operations (delete_entities, delete_observations, delete_relations) and force_sync.
Attacks that exploit this kind of access
로컬 데이터를 GitHub로 푸시합니다. It is categorised as a Write tool in the Remote Memory MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Remote Memory MCP Server MCP server in PolicyLayer and add a rule for sync_push: 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 Remote Memory MCP Server. Nothing to install.
sync_push 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 sync_push 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 sync_push. 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.
sync_push is provided by the Remote Memory MCP Server MCP server (yeomyujun/remote-memory-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 →