Write data to the VM database
AI agents use vm_data_write to create or update resources in Victoriametrics — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Victoriametrics environment.
This tool writes data into a metrics database. While writing is generally reversible in concept, injecting incorrect or malicious metrics data into a monitoring/observability database can corrupt dashboards, alerts, and operational decision-making at scale. It does not delete data, so Destructive does not apply, but the blast radius of bad writes into a shared metrics store is high.
From the tool's definition 'Write data to the VM database' — explicitly writes data into the VictoriaMetrics time-series database
Attacks that exploit this kind of access
Write data to the VM database. It is categorised as a Write tool in the Victoriametrics MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Victoriametrics MCP server in PolicyLayer and add a rule for vm_data_write: 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 Victoriametrics. Nothing to install.
vm_data_write 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 vm_data_write 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 vm_data_write. 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.
vm_data_write is provided by the Victoriametrics MCP server (@yincongcyincong/victoriametrics-mcp-server). 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 →