Return an EXPLAIN plan for a query. ANALYZE executes the query.
AI agents invoke explain_query to trigger actions in PostgreSQL SSH MCP 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.
While EXPLAIN alone is a read-only operation, the tool explicitly supports ANALYZE mode which executes the underlying query against the database. This means arbitrary SQL can be run with real side effects (DML, DDL, functions with side effects), elevating it to Execute severity. Misuse could cause data modification or expensive operations on production databases.
From the tool's definition 'ANALYZE executes the query' — the tool can actually run the query, not merely parse it
Documented attack patterns abuse exactly the kind of access explain_query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and PostgreSQL SSH MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for explain_query:
{
"version": "1",
"default": "deny",
"tools": {
"explain_query": {
"limits": [
{
"counter": "explain_query_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}explain_query 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.
Free to start. No card required.
Return an EXPLAIN plan for a query. ANALYZE executes the query. It is categorised as a Execute tool in the PostgreSQL SSH MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the PostgreSQL SSH MCP Server MCP server in PolicyLayer and add a rule for explain_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 PostgreSQL SSH MCP Server. Nothing to install.
explain_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 explain_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 explain_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.
explain_query is provided by the PostgreSQL SSH MCP Server MCP server (zlash65/postgresql-ssh-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from PostgreSQL SSH MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
12 PostgreSQL SSH MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.