inspect_schema
AI agents call inspect_schema to retrieve information from Sentinel MCP Data Governance Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Schema inspection retrieves metadata about database structure without modifying or deleting data. The tool belongs to a data governance auditing agent focused on monitoring and analysis rather than data manipulation. The sibling tools confirm this pattern of non-destructive, read-only database assessment. No side effects or data mutation is implied.
From the tool's definition Tool name 'inspect_schema' indicates schema inspection; sibling tools 'check_null_ratios', 'find_logical_anomalies', and 'get_data_health_sample' all perform read-only auditing operations without modification.
Attacks that exploit this kind of access
inspect_schema. It is categorised as a Read tool in the Sentinel MCP Data Governance Agent MCP Server, which means it retrieves data without modifying state.
Register the Sentinel MCP Data Governance Agent MCP server in PolicyLayer and add a rule for inspect_schema: 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 Sentinel MCP Data Governance Agent. Nothing to install.
inspect_schema 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 inspect_schema 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 inspect_schema. 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.
inspect_schema is provided by the Sentinel MCP Data Governance Agent MCP server (nihardugade/sentinel-mcp-data-governance-agent). 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 →