AI agents call db_catalog to retrieve information from Onpe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and returns schema/catalog information about database structure, datasets, and query presets. This is a classic Read operation: it queries metadata without side effects, does not execute arbitrary code, create/modify/delete data, or trigger external operations. The context of an electoral data query system reinforces this is informational access only.
From the tool's definition Tool name 'db_catalog' and description 'Publica datasets, presets, aliases y versión del contrato de db_query' indicate it publishes (returns/lists) metadata about available datasets, presets, and aliases—a read-only introspection operation with no data…
Attacks that exploit this kind of access
Publica datasets, presets, aliases y versión del contrato de db_query. It is categorised as a Read tool in the Onpe MCP Server, which means it retrieves data without modifying state.
Register the Onpe MCP server in PolicyLayer and add a rule for db_catalog: 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 Onpe. Nothing to install.
db_catalog 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_catalog 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_catalog. 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_catalog is provided by the Onpe MCP server (oscarzamora/onpe-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 →