local_ydb_sql
Run managed YQL v1 against the configured local-ydb target through Query Service. query uses SnapshotRO, explain returns plan/AST, and execute always runs EXPLAIN first and sends one NoTx execution only with confirm=true.
This record as markdown: /tools/local-ydb/local-ydb-sql.md
What local_ydb_sql does on Local Ydb
AI agents invoke local_ydb_sql to trigger actions in Local Ydb. 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.
Why local_ydb_sql is rated High
Executes arbitrary YQL queries against database with potential side effects depending on query content and confirmation logic.
From the tool's definition Run managed YQL v1, execute always runs EXPLAIN, sends execution
Attacks that exploit this kind of access
The rule that runs local_ydb_sql safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Local Ydb, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For local_ydb_sql, this is the rule to start with:
local_ydb_sql stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Local Ydb, apply this rule, and every local_ydb_sql call is checked against it from then on.
Questions about local_ydb_sql
Run managed YQL v1 against the configured local-ydb target through Query Service. query uses SnapshotRO, explain returns plan/AST, and execute always runs EXPLAIN first and sends one NoTx execution only with confirm=true. It is categorised as a Execute tool in the Local Ydb MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Local Ydb MCP server in PolicyLayer and add a rule for local_ydb_sql: 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 Local Ydb. Nothing to install.
local_ydb_sql 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 local_ydb_sql 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 local_ydb_sql. 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.
local_ydb_sql is provided by the Local Ydb MCP server (@astandrik/local-ydb-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Local Ydb, and thousands of servers like it.
Across the catalogue