fabric_cve_scan

[git-fabric] Scan managed repos for vulnerable dependencies via GitHub Advisory Database. Queues findings to state/cve-queue.jsonl.

Server Git Steer ry-ops/git-steer
Category Read
Risk class Low
Parameters 00 required

What fabric_cve_scan does on Git Steer

AI agents call fabric_cve_scan 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.

Why fabric_cve_scan needs a policy

This tool performs vulnerability scanning—a read-only information retrieval operation. It queries the GitHub Advisory Database for known CVEs affecting managed repositories and logs the findings to a queue for later review/action. The act of scanning and logging findings is informational; it does not execute remediation, delete data, modify code, or trigger financial transactions.

From the tool's definition Tool 'fabric_cve_scan' scans repositories and queues findings to a state file (state/cve-queue.jsonl). The core action is reading vulnerability data from GitHub Advisory Database and recording results—no modification of code, dependencies, configurations, or…

Questions about fabric_cve_scan

What does the fabric_cve_scan tool do? +

[git-fabric] Scan managed repos for vulnerable dependencies via GitHub Advisory Database. Queues findings to state/cve-queue.jsonl. It is categorised as a Read tool in the Git Steer MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on fabric_cve_scan? +

Register the Git Steer MCP server in PolicyLayer and add a rule for fabric_cve_scan: 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.

What risk level is fabric_cve_scan? +

fabric_cve_scan is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit fabric_cve_scan? +

Yes. Add a rate_limit block to the fabric_cve_scan 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.

How do I block fabric_cve_scan completely? +

Set action: deny in the PolicyLayer policy for fabric_cve_scan. 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.

What MCP server provides fabric_cve_scan? +

fabric_cve_scan 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.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.