Retry a failed job.
AI agents invoke RetryJob to trigger actions in Veeam VBR v13 MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Retrying a job triggers an external operation (re-runs a backup or replication job) on the Veeam infrastructure. It does not simply read data, nor does it irreversibly delete or overwrite data. The blast radius is medium: misuse could cause unintended resource consumption, network load, or overwrite of a backup restore point, but is generally recoverable.
From the tool's definition 'Retry a failed job' — triggers re-execution of an existing backup/replication job in Veeam VBR
Attacks that exploit this kind of access
Retry a failed job. It is categorised as a Execute tool in the Veeam VBR v13 MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Veeam VBR v13 MCP Server MCP server in PolicyLayer and add a rule for RetryJob: 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 Veeam VBR v13 MCP Server. Nothing to install.
RetryJob is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the RetryJob 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 RetryJob. 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.
RetryJob is provided by the Veeam VBR v13 MCP Server MCP server (kid-boy/veeam-mcp-13). 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 →