AI agents invoke git_push to trigger actions in Context. 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 push is an external operation that modifies a remote repository's state. While not locally destructive, it can overwrite remote history (especially with force-push), expose code publicly, trigger CI/CD pipelines, and its effects are difficult to reverse on the remote. This qualifies as Execute with high severity due to the blast radius of pushing potentially sensitive or broken code to a shared remote.
From the tool's definition 'Push current branch to remote' — triggers an external git operation that sends commits to a remote repository
Attacks that exploit this kind of access
Push current branch to remote. It is categorised as a Execute tool in the Context MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Context MCP server in PolicyLayer and add a rule for git_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 Context. Nothing to install.
git_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 git_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 git_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.
git_push is provided by the Context MCP server (vibhasdutta/context-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 →