get_forecast_percentile_history

THE RISK

Low Risk

Why get_forecast_percentile_history needs a policy

This tool retrieves historical forecast data from a prediction market. It queries and fetches information without creating, modifying, executing code, deleting data, or moving money. The operation is read-only with no side effects.

From the tool's definition Tool name 'get_forecast_percentile_history' and description 'Get historical raw and formatted forecast numbers for an event at specified percentiles' indicate data retrieval with no modification or side effects.

Documented attack patterns abuse exactly the kind of access get_forecast_percentile_history gives an agent:

POLICY

How to control get_forecast_percentile_history

PolicyLayer is an MCP gateway — it sits between your AI agents and DFlow MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_forecast_percentile_history:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_forecast_percentile_history": {}
  }
}

get_forecast_percentile_history is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register DFlow MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More DFlow MCP Server tools

Read candlestick_chart Generate ASCII candlestick chart with OHLCV data for a market. Returns a visual representa Read filter_outcome_mints Filter a list of addresses and return only outcome mints. Read get_event Get a single event by ticker. Returns event metadata including series ticker, subtitle, ma Read get_event_candlesticks Get event candlesticks from the Kalshi API. Resolves series ticker automatically. Read get_events Get a paginated list of all events with optional filtering and sorting. Read get_filters_by_sports Get filtering options for each sport including scopes and competitions. Read get_forecast_percentile_history_by_mint Get forecast history by looking up an event using a market mint address. Read get_live_data Get live data for events and markets.

All 24 DFlow MCP Server tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about get_forecast_percentile_history

What does the get_forecast_percentile_history tool do? +

Get historical raw and formatted forecast numbers for an event at specified percentiles. It is categorised as a Read tool in the DFlow MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_forecast_percentile_history? +

Register the DFlow MCP Server MCP server in PolicyLayer and add a rule for get_forecast_percentile_history: 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 DFlow MCP Server. Nothing to install.

What risk level is get_forecast_percentile_history? +

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

Can I rate-limit get_forecast_percentile_history? +

Yes. Add a rate_limit block to the get_forecast_percentile_history 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.

How do I block get_forecast_percentile_history completely? +

Set action: deny in the PolicyLayer policy for get_forecast_percentile_history. 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 get_forecast_percentile_history? +

get_forecast_percentile_history is provided by the DFlow MCP Server MCP server (opensvm/dflow-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every DFlow MCP Server tool call.

Start from DFlow MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →