AI agents invoke memento_install_git_hooks to trigger actions in Memento. 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.
This tool installs git hooks into a repository, which modifies the repository's configuration and causes code to execute automatically on future git operations (pre-commit).
From the tool's definition 'Install or update deterministic git hooks (pre-commit) for Active Coercion in the current git repository'
Attacks that exploit this kind of access
[DEPRECATED] Install or update deterministic git hooks (pre-commit) for Active Coercion in the current git repository. It is categorised as a Execute tool in the Memento MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Memento MCP server in PolicyLayer and add a rule for memento_install_git_hooks: 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 Memento. Nothing to install.
memento_install_git_hooks 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 memento_install_git_hooks 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 memento_install_git_hooks. 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.
memento_install_git_hooks is provided by the Memento MCP server (joyciakira/memento). 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 →