AI agents call fabric_git_list_pull_requests 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 queries and returns pull request data from a repository. It performs a read-only operation that does not alter any state, execute code, trigger workflows, or involve financial transactions. Even in a malicious context, an AI agent listing pull requests can only discover information; it cannot damage repositories or systems. Severity is low due to minimal blast radius.
From the tool's definition Tool name includes 'list' and description states 'List pull requests' — a retrieval operation with no modification, creation, deletion, or side effects.
Attacks that exploit this kind of access
[git-fabric] List pull requests in a repository. 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_list_pull_requests: 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_list_pull_requests 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_list_pull_requests 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_list_pull_requests. 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_list_pull_requests 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 →