AI agents call fabric_git_get_commit to retrieve information from Git Steer 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 information from Git, which is a read-only operation. It queries existing data (commit metadata and file diffs) without creating, modifying, executing, or deleting anything. The blast radius of misuse is minimal—an attacker could only gather information about repository history, which is typically already visible to users with repository access.
From the tool's definition Tool name contains 'get' and description states 'Get full details for a commit including changed files' — purely retrieves commit metadata and file change information with no side effects.
Attacks that exploit this kind of access
[git-fabric] Get full details for a commit including changed files. It is categorised as a Read tool in the Git Steer MCP Server, which means it retrieves data without modifying state.
Register the Git Steer MCP server in PolicyLayer and add a rule for fabric_git_get_commit: 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 Steer. Nothing to install.
fabric_git_get_commit 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 fabric_git_get_commit 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 fabric_git_get_commit. 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.
fabric_git_get_commit is provided by the Git Steer MCP server (ry-ops/git-steer). 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 →