AI agents call vex_history 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 and queries vulnerability exemption (VEX) history data without side effects. It provides audit/compliance visibility into VEX record changes but does not create, modify, delete, or trigger external operations. The append-only nature of the ledger and read-only query operations confirm Read category classification with low severity risk.
From the tool's definition Tool performs lookups ('Look up VEX history') from an append-only ledger, returning historical records and current status.
Attacks that exploit this kind of access
Look up VEX history from the append-only vex.jsonl ledger (who/what/when, before -> after). Filter by repo and/or cveId. Returns chronological history plus the current status. 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 vex_history: 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.
vex_history 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 vex_history 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 vex_history. 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.
vex_history 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 →