Update records in a table
AI agents use update to create or update resources in Bun Database MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Bun Database MCP Server environment.
The update operation modifies existing records but does not irreversibly delete or destroy data. While the server claims parameterized queries and SQL injection prevention, an AI agent could still misuse this to modify incorrect records or overwrite sensitive fields at scale. Severity is medium because updates are reversible (can be rolled back or corrected), and the server implements mitigations.
From the tool's definition Tool name is 'update' and description states 'Update records in a table' — this creates or modifies data reversibly.
Attacks that exploit this kind of access
Update records in a table. It is categorised as a Write tool in the Bun Database MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Bun Database MCP Server MCP server in PolicyLayer and add a rule for update: 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 Bun Database MCP Server. Nothing to install.
update 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 update 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 update. 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.
update is provided by the Bun Database MCP Server MCP server (ross-jill-ws/bun-db-mcp). 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 →