// SCAN REPORT

Radar

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

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

Last updated: 20 Aug 2026

0 can modify or destroy data

6 read-only

6 tools total

Community server · catalogue entry checked 20/08/2026 · full schemas captured for 6 of 6 tools

How to control Radar ↓

TOOL MAP

What Radar exposes to your agents

Read (6) Write / Execute (0) Destructive / Financial (0)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Radar costs in tokens

1,150 tokens of tool definitions, loaded on every request

0.6% of a 200k context window

236 heaviest tool: funding_history

Full per-tool breakdown → Model it in the token calculator →

THE RISK

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.

POLICY

How to control Radar

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

Cap read operations

{
  "funding_events": {
    "limits": [
      {
        "counter": "funding_events_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

Create a free account and register Radar — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON RADAR →

Instant setup, no code required.

FULL CATALOGUE

All 6 Radar tools

READ 6 tools

Read funding_events What is burning on the crypto perpetuals funding market right now: open extreme events (|hourly rate| ≥ 0.1%/h Read funding_history Charged funding rates of one coin across all exchanges where it trades, normalized to %/hour on a common hourl Read pair_briefing Everything the radar knows about one perpetual pair in a single answer: funding rate and receiving side, time Read radar_about Reference about Funding Radar itself: which exchanges and how many pairs it covers, how fresh the data is, a g Read settlement_calendar Which notable funding settlements are coming in the next hours (default 4): pairs with |rate| ≥ 0.05%/h and vo Read spread_pairs Where the funding-rate spread between exchanges is widest right now: long leg on the low-rate exchange, short

FAQ

Questions about Radar

Is the Radar MCP server safe to use without restrictions? +

The Radar server is primarily read-only with 6 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 Radar MCP server expose? +

6 tools across 1 categories: Read. 6 are read-only. 0 can modify, create, or delete data.

How do I enforce a policy on Radar? +

Register the Radar 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 Radar tool call.

Deterministic rules across all 6 Radar tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON RADAR →

Instant setup, no code required.

6 Radar tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Radar's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →