ops_database_query
Execute one read-only MySQL, PostgreSQL or SQLite SELECT on a saved source. Every referenced base table must be outside the disabled-table list; system databases and PostgreSQL system schemas are unavailable. PostgreSQL unqualified tables resolve to public. Supports filtering, aggregation and joi...
This record as markdown: /tools/dutydeck/ops-database-query.md
What ops_database_query does on DutyDeck
AI agents call ops_database_query to retrieve information from DutyDeck without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why ops_database_query is rated Low
Even though ops_database_query only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs ops_database_query safely
PolicyLayer is an MCP gateway: it sits between your AI agents and DutyDeck, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For ops_database_query, this is the rule to start with:
ops_database_query is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect DutyDeck, apply this rule, and every ops_database_query call is checked against it from then on.
Questions about ops_database_query
Execute one read-only MySQL, PostgreSQL or SQLite SELECT on a saved source. Every referenced base table must be outside the disabled-table list; system databases and PostgreSQL system schemas are unavailable. PostgreSQL unqualified tables resolve to public. Supports filtering, aggregation and joins within the named database. No comments, subqueries, CTEs, UNION, views, protected fields, writes, locking, user variables or arbitrary functions. Single-table and join queries share a ${SERVER_OPS_DATA_QUERY_TIMEOUT_MS / 1_000}-second execution limit; returns at most 50 rows and a bounded result size. After a timeout, do not repeatedly retry unchanged SQL or bypass limits through SSH/Shell; narrow filters, reduce joined tables or inspect indexes first. SQL literals are omitted from audit.${UNTRUSTED_EVIDENCE}. It is categorised as a Read tool in the DutyDeck MCP Server, which means it retrieves data without modifying state.
Register the DutyDeck MCP server in PolicyLayer and add a rule for ops_database_query: 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 DutyDeck. Nothing to install.
ops_database_query 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 ops_database_query 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 ops_database_query. 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.
ops_database_query is provided by the DutyDeck MCP server (taokoplay/DutyDeck). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on DutyDeck, and thousands of servers like it.
This server
Across the catalogue