Execute SQL queries on SQLite databases within the workspace
AI agents invoke database_query to trigger actions in MCP Workspace Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes arbitrary SQL queries, which can include not just SELECT statements but also INSERT, UPDATE, DELETE, DROP, and other DDL/DML operations. Since it permits arbitrary SQL execution, it spans from Read all the way to Destructive. Per the rules, the most severe applicable category is chosen.
From the tool's definition 'Execute SQL queries on SQLite databases within the workspace'
Attacks that exploit this kind of access
Execute SQL queries on SQLite databases within the workspace. It is categorised as a Execute tool in the MCP Workspace Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Workspace Server MCP server in PolicyLayer and add a rule for 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 MCP Workspace Server. Nothing to install.
database_query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the 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 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.
database_query is provided by the MCP Workspace Server MCP server (shayyeffet/ultimate_mcp_server). 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 →