Read-only PostgreSQL SELECT over financial / market / alt-data tables — returns structured rows. Hard rules (query fails otherwise): - SELECT only, no CTE (WITH ... AS) — use subqueries. - Date/period columns are TEXT — compare as strings (period_end >= '2024-01'). No ::date cast, no INTERVAL mat...
Risk signalsAccepts freeform code/query input (sql)
Part of the Drillr — The financial MCP for AI agents server.
Free to start. No card required.
AI agents invoke run_sql to trigger processes or run actions in Drillr — The financial MCP for AI agents. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
run_sql can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
{
"version": "1",
"default": "deny",
"tools": {
"run_sql": {
"limits": [
{
"counter": "run_sql_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}See the full Drillr — The financial MCP for AI agents policy for all 9 tools.
These attack patterns abuse exactly the kind of access run_sql gives an agent. Each links to the full case and the policy that stops it:
Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Read-only PostgreSQL SELECT over financial / market / alt-data tables — returns structured rows. Hard rules (query fails otherwise): - SELECT only, no CTE (WITH ... AS) — use subqueries. - Date/period columns are TEXT — compare as strings (period_end >= '2024-01'). No ::date cast, no INTERVAL math. - No ROUND(float8, int) — use CAST(x AS DECIMAL(10,2)) when rounding. - Filter structured tables by ticker (WHERE ticker IN ('AAPL','MSFT'); screening: add ticker NOT LIKE '%-%' to drop preferred stock). Alt-data is macro/industry — no ticker filter. Before querying a table, call get_table_schema(table) — it returns that table's columns PLUS its required filters, gotchas, and ticker formats. For alt-data tables call list_tables(categories=[...]) to discover them. Sibling tools: SEC filing narrative → sec_report_search; qualitative company discovery → company_search; recent news / market events → signal_list. Tables by domain (call get_table_schema for detail): - Market: price_volume_history (OHLCV history; MUST filter ticker + time_frame), index_price, equity_extended_rt (pre/after/overnight quotes) - Fundamentals: financial_statements (GAAP income/balance/cashflow), company_snapshot (ratios, per-share, growth) - Earnings: earning_call_summary, earning_call_calendar - Analyst: analyst_ratings, analyst_ratings_consensus - Ownership: insider_and_institution_activities - 8-K events: executive_change, company_deal_events, debt_issuance, securities_offering - Executives: executive_profile, executive_compensation - Alt-data: macro / industry / trade / AI-supply-chain — call list_tables(categories=[...]). It is categorised as a Execute tool in the Drillr — The financial MCP for AI agents MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Drillr — The financial MCP for AI agents MCP server in PolicyLayer and add a rule for run_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 Drillr — The financial MCP for AI agents. Nothing to install.
run_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 run_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 run_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.
run_sql is provided by the Drillr — The financial MCP for AI agents MCP server (https://gateway.drillr.ai/mcp/data). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 9 Drillr — The financial MCP for AI agents tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.