List commits. since/until are ISO 8601 timestamps.
AI agents call list_commits to retrieve information from GitLab MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical commit data from a repository using standard query filters (since/until timestamps). It performs no mutations, does not execute code, and does not delete or modify data. It is a straightforward read operation with minimal blast radius if misused by an agent—worst case exposure of repository history that is typically already visible to authenticated users.
From the tool's definition Tool name is 'list_commits' and description states 'List commits' with filtering by timestamp parameters. The verb 'list' and the read-only nature of querying commit history indicate no data modification or side effects.
Attacks that exploit this kind of access
List commits. since/until are ISO 8601 timestamps. It is categorised as a Read tool in the GitLab MCP MCP Server, which means it retrieves data without modifying state.
Register the GitLab MCP server in PolicyLayer and add a rule for list_commits: 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 GitLab MCP. Nothing to install.
list_commits 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 list_commits 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 list_commits. 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.
list_commits is provided by the GitLab MCP server (shahabmosavi/gitlab_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 →