Ejecuta un comando de git (checkout, status, branch) en una carpeta local permitida.
AI agents invoke ejecutar_git_local to trigger actions in Modular 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.
The tool executes git commands in a local folder. While the listed examples (checkout, status, branch) are relatively benign, the tool runs arbitrary git commands which could include destructive operations (e.g., git reset --hard, git clean -fd, git push --force).
From the tool's definition "Ejecuta un comando de git (checkout, status, branch) en una carpeta local permitida"
Attacks that exploit this kind of access
Ejecuta un comando de git (checkout, status, branch) en una carpeta local permitida. It is categorised as a Execute tool in the Modular MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Modular MCP Server MCP server in PolicyLayer and add a rule for ejecutar_git_local: 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 Modular MCP Server. Nothing to install.
ejecutar_git_local 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 ejecutar_git_local 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 ejecutar_git_local. 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.
ejecutar_git_local is provided by the Modular MCP Server MCP server (satanas66/tfm-mcp-062026). 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 →