Low Risk

stock_data_query

Stock prices, earnings, revenue, P/E, dividends, margins, screener, comparisons Run a SQL query against 64 years of US stock market data. Use this after calling unlock_financial_analysis. Supports stock screening, fundamental analysis, technical analysis, company comparisons, and backtesting ac...

Accepts freeform code/query input (sql)

Part of the Shibui Finance MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

AI agents call stock_data_query to retrieve information from Shibui Finance without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

Even though stock_data_query only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

shibui-finance.yaml
tools:
  stock_data_query:
    rules:
      - action: allow

See the full Shibui Finance policy for all 2 tools.

Tool Name stock_data_query
Category Read
Risk Level Low

Agents calling read-class tools like stock_data_query have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.

What does the stock_data_query tool do? +

Stock prices, earnings, revenue, P/E, dividends, margins, screener, comparisons Run a SQL query against 64 years of US stock market data. Use this after calling unlock_financial_analysis. Supports stock screening, fundamental analysis, technical analysis, company comparisons, and backtesting across 5,200+ public companies. Key tables: stock_quotes, earnings_quarterly (EPS estimates/actuals/ surprise %), income_statement, balance_sheet, cash_flow, technical_indicators, highlights (market cap, P/E, margins).. It is categorised as a Read tool in the Shibui Finance MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on stock_data_query? +

Add a rule in your Intercept YAML policy under the tools section for stock_data_query. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Shibui Finance MCP server.

What risk level is stock_data_query? +

stock_data_query is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit stock_data_query? +

Yes. Add a rate_limit block to the stock_data_query rule in your Intercept 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.

How do I block stock_data_query completely? +

Set action: deny in the Intercept policy for stock_data_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.

What MCP server provides stock_data_query? +

stock_data_query is provided by the Shibui Finance MCP server (shibui/finance). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Let agents act without letting them run wild.

Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.