Sample rows from a table (max 100 rows). Read-only, with automatic row limit guardrails.
AI agents call db_sample_values to retrieve information from RunContext without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves data from a database table with built-in protections (max 100 rows, read-only mode). It has no side effects, cannot modify or delete data, and poses minimal risk. It falls squarely into the Read category. The guardrails further reduce severity to low.
From the tool's definition Tool description explicitly states 'Sample rows from a table' and 'Read-only, with automatic row limit guardrails.' The name 'db_sample_values' and description make clear this retrieves data without modification.
Attacks that exploit this kind of access
Sample rows from a table (max 100 rows). Read-only, with automatic row limit guardrails. It is categorised as a Read tool in the RunContext MCP Server, which means it retrieves data without modifying state.
Register the RunContext MCP server in PolicyLayer and add a rule for db_sample_values: 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 RunContext. Nothing to install.
db_sample_values is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the db_sample_values 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 db_sample_values. 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.
db_sample_values is provided by the RunContext MCP server (quiet-victory-labs/runcontext). 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 →