Grok Crypto Quant API MCP server
dev.fly.grok-backtest-api/crypto-quantgrok-backtest-api.fly.devstreamable-httpv0.3.0Scanned
Bias-free crypto backtests (399 coins), signals, token scam checks. Free samples; pay via x402 USDC.
13 tools: 6 change things and 7 only read.
- Reads private data · 0
- Reads text others write · 13
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
6 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Grok Crypto Quant API MCP server can do
The Grok Crypto Quant API MCP server is published by grok-backtest-api.fly.dev, a domain the MCP Registry verified. It has 13 tools. It can create or change data (6 tools: backtest, market_signals, token_check, signals_sample and 2 more), but cannot delete data. 7 tools only read.
13 tools bring in text other people can write (backtest, market_signals, token_check and 10 more).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 10, 2026, version 0.3.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
13 tools
Changes things 6Claude Code: ask
backtestBacktest crypto strategies on 399 Coinbase coins without survivorship bias.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Backtest crypto strategies on 399 Coinbase coins without survivorship bias. DIY backtests usually use today's coin list, so dead coins vanish and returns are overstated; this rebuilds the universe from each past day's top coins. Breakout, momentum, dip-buy or MA-trend rules on daily data with fees, slippage, H1/H2 split and a luck flag. No data fetching or backtest code on your side. Price: $0.05 USDC per call (x402, Base mainnet). Free pre-check: validate_backtest. Free sample: backtest_sample.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
backtest_sampleFree sample of the paid `backtest` tool on the same survivorship-bias-free engine: any strategy, point-in-time top-10 universe, window = last `days` (14..90) completed days, summar…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Free sample of the paid `backtest` tool on the same survivorship-bias-free engine: any strategy, point-in-time top-10 universe, window = last `days` (14..90) completed days, summary only. Full version: backtest ($0.05). Limit 30/hour per client.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
healthFree: service status, prices, network and data range.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Free: service status, prices, network and data range.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
market_signalsDaily crypto market regime in one call: BTC/ETH vs 20/50-day MAs, breadth of the point-in-time top-N (no survivorship bias), coins nearest a 20-day breakout, and the R1 breakout st…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Daily crypto market regime in one call: BTC/ETH vs 20/50-day MAs, breadth of the point-in-time top-N (no survivorship bias), coins nearest a 20-day breakout, and the R1 breakout strategy's gate and entry signals. No candle fetching or indicator code. Completed UTC daily closes only. Price: $0.01 USDC per call (x402, Base mainnet). Free sample: signals_sample.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
signals_sampleFree, one day delayed: yesterday's full /signals result (BTC/ETH trend, breadth, breakout watchlist, R1 gate) so you can judge quality before paying.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Free, one day delayed: yesterday's full /signals result (BTC/ETH trend, breadth, breakout watchlist, R1 gate) so you can judge quality before paying. Today's result: paid market_signals ($0.01). Limit 60/hour per client.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
token_checkToken scam check in one call instead of wiring up five data sources: honeypot sell simulation, unverified code, mint/pause/blacklist powers, taxes, upgradeable proxy, age, liquidit…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Token scam check in one call instead of wiring up five data sources: honeypot sell simulation, unverified code, mint/pause/blacklist powers, taxes, upgradeable proxy, age, liquidity, fake major-token (e.g. fake USDC) lookalikes and spam-airdrop patterns. Base, Ethereum or Solana. Never visits metadata URLs. Price: $0.02 USDC per call (x402, Base mainnet). Free pre-check: validate_token_check.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 7Show 7 read-only tools
get_schemaFree: request schemas, examples, prices and limits for every paid tool/endpoint.Reads text others writeNo findings
Why it is in this group
- The name "get_schema" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Free: request schemas, examples, prices and limits for every paid tool/endpoint.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
optimize_strategyFind robust strategy params, not lucky ones: tests up to 50 combos on the same survivorship-bias-free backtester, ranks by worst-half (H1/H2) return with neighbourhood smoothing, f…Reads text others writeNo findings
Why it is in this group
- The description's first verb is "find": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Find robust strategy params, not lucky ones: tests up to 50 combos on the same survivorship-bias-free backtester, ranks by worst-half (H1/H2) return with neighbourhood smoothing, flags overfitting, and recommends the most stable parameters rather than the best-fit ones. Price: $0.50 USDC per call (x402, Base mainnet). Free pre-check: validate_optimize.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
universe_snapshotSurvivorship-free top-N coin list for any past date: Coinbase USD pairs ranked by trailing 20-day dollar volume using only data available that day.Reads text others writeNo findings
Why it is in this group
- The name "universe_snapshot" says "snapshot": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Survivorship-free top-N coin list for any past date: Coinbase USD pairs ranked by trailing 20-day dollar volume using only data available that day. Fixes your own backtests: picking today's top coins hides the ones that died and overstates returns. Price: $0.05 USDC per call (x402, Base mainnet). Free pre-check: validate_universe.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
validate_backtestFree: check backtest arguments (same as the paid `backtest` tool) before paying.Reads text others writeNo findings
Why it is in this group
- The name "validate_backtest" says "validate": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Free: check backtest arguments (same as the paid `backtest` tool) before paying.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
validate_optimizeFree: check optimize_strategy arguments and count grid combos before paying.Reads text others writeNo findings
Why it is in this group
- The name "validate_optimize" says "validate": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Free: check optimize_strategy arguments and count grid combos before paying.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
validate_token_checkFree: format-check a token_check request (no on-chain lookups).Reads text others writeNo findings
Why it is in this group
- The name "validate_token_check" says "validate": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Free: format-check a token_check request (no on-chain lookups).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
validate_universeFree: check universe_snapshot arguments (date in range, enough history) before paying.Reads text others writeNo findings
Why it is in this group
- The name "validate_universe" says "validate": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Free: check universe_snapshot arguments (date in range, enough history) before paying.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write13
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 18, 2026, 16:24 UTC, unchanged since Oct 27, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 6
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 6 tools that change things (6 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://grok-backtest-api.fly.dev/mcp: tools/list returned 13 tools to an anonymous client, including backtest (write), market_signals (write), token_check (write), signals_sample (write), backtest_sample (write) and 1 more
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools2 added, 5 changed.+2 added~5 changedView diff
- Added:backtest_sampleChanges things
- Added:signals_sampleChanges things
- Changed:backtestChanges thingsdescription
- Changed:market_signalsChanges thingsdescription
- Changed:optimize_strategyOnly readsdescription
- Changed:token_checkChanges thingsdescription
- Changed:universe_snapshotOnly readsdescription
Install
Pinned to version 0.3.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http crypto-quant https://grok-backtest-api.fly.dev/mcpclaude mcp add --transport http crypto-quant https://grok-backtest-api.fly.dev/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__crypto-quant__optimize_strategy",
"mcp__crypto-quant__universe_snapshot",
"mcp__crypto-quant__get_schema",
"mcp__crypto-quant__validate_backtest",
"mcp__crypto-quant__validate_optimize",
"mcp__crypto-quant__validate_token_check",
"mcp__crypto-quant__validate_universe"
],
"ask": [
"mcp__crypto-quant__backtest",
"mcp__crypto-quant__market_signals",
"mcp__crypto-quant__token_check",
"mcp__crypto-quant__signals_sample",
"mcp__crypto-quant__backtest_sample",
"mcp__crypto-quant__health"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as crypto-quant. Review it before you use it.
Capability tags behind 13 rules
- mcp__crypto-quant__backtest untrusted-input
- mcp__crypto-quant__market_signals untrusted-input
- mcp__crypto-quant__token_check untrusted-input
- mcp__crypto-quant__optimize_strategy untrusted-input
- mcp__crypto-quant__universe_snapshot untrusted-input
- mcp__crypto-quant__signals_sample untrusted-input
- mcp__crypto-quant__backtest_sample untrusted-input
- mcp__crypto-quant__health untrusted-input
- mcp__crypto-quant__get_schema untrusted-input
- mcp__crypto-quant__validate_backtest untrusted-input
- mcp__crypto-quant__validate_optimize untrusted-input
- mcp__crypto-quant__validate_token_check untrusted-input
- mcp__crypto-quant__validate_universe untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/dev.fly.grok-backtest-api/crypto-quant/verify?hash=b665ac7f4af79c078dc1f863f318125b89640b1db5804f2ec93e6e38c595b7d8" | jq -e '.changed == false'Pinned hash b665ac7f4af7, from Nov 10, 2026, 21:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/dev.fly.grok-backtest-api/crypto-quant/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/dev.fly.grok-backtest-api/crypto-quant)Source: MCP Registry. Synced Oct 29, 2026, 12:17 UTC.
Grok Crypto Quant API MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Grok Crypto Quant API MCP server safe?
- No scan can promise that. What its definitions show: 13 tools, 6 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Grok Crypto Quant API MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Grok Crypto Quant API MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Grok Crypto Quant API MCP server have?
- 13 tools: 6 write, 7 read. backtest, market_signals, token_check, signals_sample, backtest_sample, health, optimize_strategy, universe_snapshot and 5 more.
Does the Grok Crypto Quant API MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Grok Crypto Quant API MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Grok Crypto Quant API MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Oct 29, 2026. Every change is on this page and in its Atom feed.