Load backtesting workflow for signal testing, forward returns, win rates. REQUIRES get_database_schema then get_query_patterns to be called first (in that order). Call BEFORE writing SQL when the user asks to backtest, test a strategy, check "what happens after X", compare forward returns, measur...
Part of the Shibui Finance server.
Free to start. No card required.
AI agents call load_backtesting_workflow 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 load_backtesting_workflow 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.
{
"version": "1",
"default": "deny",
"tools": {
"load_backtesting_workflow": {}
}
}See the full Shibui Finance policy for all 11 tools.
These attack patterns abuse exactly the kind of access load_backtesting_workflow gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Load backtesting workflow for signal testing, forward returns, win rates. REQUIRES get_database_schema then get_query_patterns to be called first (in that order). Call BEFORE writing SQL when the user asks to backtest, test a strategy, check "what happens after X", compare forward returns, measure win rates, "is it better to buy when X vs Y", evaluate trading signals historically, or compute any hypothetical return over past data. Contains hard rules for survivorship bias, outlier handling, sampling design, and risk-adjusted metrics (Sharpe, Sortino, drawdown). Can be combined with other workflow tools.. It is categorised as a Read tool in the Shibui Finance MCP Server, which means it retrieves data without modifying state.
Register the Shibui Finance MCP server in PolicyLayer and add a rule for load_backtesting_workflow: 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 Shibui Finance. Nothing to install.
load_backtesting_workflow is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the load_backtesting_workflow 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 load_backtesting_workflow. 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.
load_backtesting_workflow is provided by the Shibui Finance MCP server (https://mcp.shibui.finance/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 11 Shibui Finance 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.