AI agents call report_generate 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 reads and aggregates existing state data to produce reports. It does not modify, delete, or execute anything — it queries stored audit logs and configuration to render predefined report templates (executive-summary, change-records, vulnerability-report, full-audit). Pure read/reporting operation with low blast radius if misused.
From the tool's definition Generate compliance and security reports from git-steer state data
Attacks that exploit this kind of access
Generate compliance and security reports from git-steer state data. Templates: executive-summary, change-records, vulnerability-report, full-audit. 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 report_generate: 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.
report_generate 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 report_generate 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 report_generate. 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.
report_generate 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 →