AI agents call git_list_remotes to retrieve information from Git without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays existing Git remote configurations. It does not create, modify, delete, or execute any operations—it simply queries and returns metadata about the repository's remote endpoints. This is a straightforward Read operation with minimal risk; knowing remote URLs does not enable unauthorized access without valid credentials.
From the tool's definition Tool description: 'List configured repository remotes with fetch and push URLs.' The verb 'List' and the read-only nature of querying remote configuration indicate pure information retrieval with no side effects.
Attacks that exploit this kind of access
List configured repository remotes with fetch and push URLs. It is categorised as a Read tool in the Git MCP Server, which means it retrieves data without modifying state.
Register the Git MCP server in PolicyLayer and add a rule for git_list_remotes: 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 Git. Nothing to install.
git_list_remotes is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the git_list_remotes 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_list_remotes. 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_list_remotes is provided by the Git MCP server (selfagency/git-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 →