AI agents use vex_set to create or update resources in Git Steer — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Git Steer environment.
This tool modifies vulnerability metadata by writing OpenVEX status records (not_affected or affected) to a persistent state repository. While not destructive (the operation is reversible and does not delete data), and not financial, it is a write operation that creates or modifies vulnerability tracking records.
From the tool's definition Set OpenVEX status on a CVE finding (ADR-004). Persisted to the git-steer-state _vex store.
Attacks that exploit this kind of access
Set OpenVEX status on a CVE finding (ADR-004). Persisted to the git-steer-state _vex store. not_affected requires a justification; affected requires an actionStatement. It is categorised as a Write tool in the Git Steer MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Git Steer MCP server in PolicyLayer and add a rule for vex_set: 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_set is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the vex_set 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_set. 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_set 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 →