Run git commands in a repository.
AI agents invoke git to trigger actions in MCP Build Environment Service. 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 commands span multiple operation types (read, write, destructive) depending on arguments: `git log` is read-only, but `git push --force` can overwrite remote history, `git reset --hard` can destroy local work, and `git clone` can execute arbitrary code from repository hooks.
From the tool's definition Tool description states 'Run git commands in a repository' - this executes arbitrary git operations whose effects depend on arguments provided by the AI agent.
Attacks that exploit this kind of access
Run git commands in a repository. It is categorised as a Execute tool in the MCP Build Environment Service MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Build Environment Service MCP server in PolicyLayer and add a rule for git: 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 MCP Build Environment Service. Nothing to install.
git 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 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. 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 is provided by the MCP Build Environment Service MCP server (jbroll/mcp-build). 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 →