DFlow MCP Server

24 tools. 0 can modify or destroy data without limits.

Read-only server. Low risk, but rate limits prevent runaway API costs.

Last updated:

0 can modify or destroy data
24 read-only
24 tools total

Community server · catalogue entry verified 12/06/2026

How to control DFlow MCP Server ↓

What DFlow MCP Server exposes to your agents

Read (24) Write / Execute (0) Destructive / Financial (0)

What can go wrong

Even read-only tools carry cost. An agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up bills.

How to control DFlow MCP Server

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

Cap read operations
{
  "candlestick_chart": {
    "limits": [
      {
        "counter": "candlestick_chart_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register DFlow MCP Server — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON DFLOW →

Free to start. No card required.

All 24 DFlow MCP Server tools

READ 24 tools
Read candlestick_chart Generate ASCII candlestick chart with OHLCV data for a market. Returns a visual representation of price moveme 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, markets, strike inform 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 Get historical raw and formatted forecast numbers for an event at specified percentiles. 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. Read get_live_data_by_event Get live data for all milestones of an event. Read get_live_data_by_mint Get live data by looking up an event from a market mint address. Read get_market Get details of a market by ticker. Read get_market_by_mint Get market details by token mint address. Read get_market_candlesticks Get market candlesticks. Resolves series ticker automatically. Read get_market_candlesticks_by_mint Get candlesticks by looking up a market by mint address. Read get_markets Get a paginated list of markets with optional filtering. Read get_markets_batch Get multiple markets by tickers and/or mint addresses (up to 100 results). Read get_outcome_mints Get a flat list of yes and no outcome mint pubkeys. Read get_series Get all series templates with optional filtering. Read get_series_by_ticker Get a single series by its ticker. Read get_tags_by_categories Get a mapping of series categories to tags. Read get_trades Get a paginated list of trades across markets with optional filtering. Read get_trades_by_mint Get trades for a market identified by a mint address. Read search_events Search events with nested markets by title or ticker.

Questions about DFlow MCP Server

Is the DFlow MCP Server MCP server safe to use without restrictions? +

The DFlow MCP Server server is primarily read-only with 24 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the DFlow MCP Server MCP server expose? +

24 tools across 1 categories: Read. 24 are read-only. 0 can modify, create, or delete data.

How do I enforce a policy on DFlow MCP Server? +

Register the DFlow MCP Server MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every DFlow MCP Server tool call.

Deterministic rules across all 24 DFlow MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

24 DFlow MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.