Push the current branch to the specified remote with optional upstream/force settings.
AI agents invoke github_review_push to trigger actions in Promethean OS MCP. 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.
Pushing to a remote repository is an external operation that modifies the remote state. The 'force' option makes this potentially destructive (force-push can overwrite remote history irreversibly), but since it's optional and the primary action is a push operation, Execute is the most appropriate base category.
From the tool's definition Push the current branch to the specified remote with optional upstream/force settings
Attacks that exploit this kind of access
Push the current branch to the specified remote with optional upstream/force settings. It is categorised as a Execute tool in the Promethean OS MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Promethean OS MCP server in PolicyLayer and add a rule for github_review_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 Promethean OS MCP. Nothing to install.
github_review_push 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 github_review_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 github_review_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.
github_review_push is provided by the Promethean OS MCP server (octave-commons/mcp). 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 →