AI agents use vikingdb-upsert-information to create or update resources in VikingDB — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your VikingDB environment.
Upsert (update or insert) is a reversible modification operation that creates new records or updates existing ones. This is characteristic of Write operations. Severity is medium because unintended upserts could pollute the data store with incorrect information, but the operation is reversible through subsequent overwrites or deletes.
From the tool's definition Tool description states 'upsert information to vikingdb' — upsert is a standard write operation that creates or modifies data reversibly.
Attacks that exploit this kind of access
upsert information to vikingdb for later use. It is categorised as a Write tool in the VikingDB MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the VikingDB MCP server in PolicyLayer and add a rule for vikingdb-upsert-information: 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 VikingDB. Nothing to install.
vikingdb-upsert-information 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 vikingdb-upsert-information 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 vikingdb-upsert-information. 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.
vikingdb-upsert-information is provided by the VikingDB MCP server (kashiwabyte/vikingdb-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 →