Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

copy.top

REMOTE · COPY.TOP

Live signals, trader intel and alerts from top fomo, pump.fun and hyperliquid traders. Read-only.

Available components

+6 this week 75 Trust /100

Last scanned (17 hours ago)

Scores higher than 62% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Crypto and Web3

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security80
  • The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
  • No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
  • HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
  • The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
  • DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
Schema Quality & AI Usability79
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1862 tokens (~116/item across 16 items; 16 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management23
  • Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage87
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 61% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 16 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 17 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Nov 26 +3
    • The server rewrote its instructions, which are the text every model session reads security
    • Schema quality: pass → fail ▼ functional
    • Tool coverage: 53% → 61% ▲ functional
    • The server now declares the “prompts” capability functional
    • First check of Schema quality: 100 functional
    • New prompt “analyze_coin” functional
    • New prompt “check_trader” functional
    • New prompt “find_trader_to_copy” functional
    • New prompt “hyperliquid_read” functional
    • New prompt “market_recap” functional
    • New prompt “watch_signals” functional
    • “get_alerts” added an optional parameter “limit” cosmetic
    • “get_dex_paid” added an optional parameter “limit” cosmetic
    • “get_hot_coins” added an optional parameter “limit” cosmetic
    • “get_hot_index” added an optional parameter “limit” cosmetic
    • “get_live_trades” added an optional parameter “limit” cosmetic
    • “get_money_flow” added an optional parameter “limit” cosmetic
    • “get_theses” added an optional parameter “limit” cosmetic
  • 20 Nov 26 +1
    • Tool coverage: 46% → 53% ▲ functional
    • Schema quality: fail → pass ▲ functional
    • Server version: 0.2.0 → 0.2.1 functional
    • New tool “hl_get_calls” functional
    • New tool “hl_get_market_read” functional
    • New tool “hl_get_markets” functional
    • New tool “hl_get_trader” functional
    • New tool “hl_get_traders” functional
  • 18 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Nov 26 0
    • Stability: unverified → 0.03 ▲ functional
  • 14 Nov 26 69

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://copy.top/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=copy.top CN=YE2,O=Let's Encrypt,C=US 30 Sept 2026 29 Dec 2026 ECDSA 256 ECDSA-SHA384 5e1c5cdab786668e2864c8e43734ebc87b3
SANs: *.copy.top, copy.top
CN=YE2,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 4df3b15dd6c0784c507cd37b58e6f115
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of copy.top. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
top. DS published 41508 13 Verified
copy.top. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=31536000; includeSubDomains
content-security-policy frame-ancestors https://web.telegram.org; base-uri 'self'; object-src 'none'
x-content-type-options nosniff
referrer-policy strict-origin-when-cross-origin

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://copy.top/mcp Verified 200
http (plaintext) http://copy.top/mcp HTTPS enforced 301 https://copy.top/mcp
MCP tools · 16 exposed · ~1,465 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
get_alerts ~177

events since a cursor, for alert bots: confluence (several top traders bought the same coin recently), big_trade (one tracked trader bought or sold a large amount) and thesis (a tracked trader posted a thesis). pass the cursor of the previous call as since; without since, the last 15 minutes. thresholds are yours.

NameTypeReqDescription
kindsarray––
limitinteger–rows to return, default 40. ask for fewer to get a shorter answer
max_mcap_usdnumber–ignore coins above this market cap
min_top_tradersinteger–confluence threshold, default 3
min_trade_usdnumber–big trade threshold in dollars, default 5000
sincestring–the cursor of the previous call (iso time)

No output schema declared.

No examples provided.

get_dex_paid ~70

coins whose team paid for a dexscreener profile in the last 24 h (a sign the team is spending), with price, market cap, liquidity, volume and moves.

NameTypeReqDescription
limitinteger–rows to return, default 12. ask for fewer to get a shorter answer

No output schema declared.

No examples provided.

get_hot_coins ~105

the signal feed: coins tracked traders are buying now. window 1h or 24h, optional max market cap in dollars. each coin: how many traders and top traders bought, dollars bought and sold, minutes since the first buy, and the first buyers.

NameTypeReqDescription
limitinteger–rows to return, default 15. ask for fewer to get a shorter answer
max_mcap_usdnumber––
windowstringyes–

No output schema declared.

No examples provided.

get_hot_index ~100

copy.top's hot index: coins ranked 0-100 by attention right now, mixing tracked traders buying, callers and x activity (voices, views). window 1h, 6h or 24h; optional chain.

NameTypeReqDescription
chainstring–chain id as the tools give it
limitinteger–rows to return, default 10. ask for fewer to get a shorter answer
windowstring––

No output schema declared.

No examples provided.

get_leaderboard ~123

rank traders like copy.top's discover page. window 1d, 7d or 30d; sort total (pnl), realized, roi, winrate or copiers; optional chain or platform (fomo, pumpfun); fair_play clean or clean_or_watch keeps only those.

NameTypeReqDescription
chainstring–chain id as the tools give it
fair_playstring––
limitinteger–default 10
platformstring––
sortstringyes–
windowstringyes–

No output schema declared.

No examples provided.

get_live_trades ~118

the live tape: the latest buys and sells by tracked traders (fomo and pump.fun), newest first. optional since (iso time or the cursor of a previous call) to get only newer trades, side buy or sell, min_usd.

NameTypeReqDescription
limitinteger–rows to return, default 30. ask for fewer to get a shorter answer
min_usdnumber––
sidestring––
sincestring–iso time, e.g. the cursor from the previous call

No output schema declared.

No examples provided.

get_money_flow ~91

where tracked traders' dollars go: coins ranked by dollars bought (side buy) or sold (side sell) over 1h, 6h, 24h or 7d, with the number of traders.

NameTypeReqDescription
limitinteger–rows to return, default 10. ask for fewer to get a shorter answer
sidestringyes–
windowstringyes–

No output schema declared.

No examples provided.

get_theses ~88

the latest or most popular theses (a trader's written reason for holding a coin) posted by tracked traders in the last 24 h at most, with the coin and their pnl at post.

NameTypeReqDescription
hoursinteger–default 24
limitinteger–rows to return, default 10. ask for fewer to get a shorter answer
sortstringyes–

No output schema declared.

No examples provided.

get_token ~70

a coin's copy.top page: price, market cap, 1h and 24h moves, liquidity, which tracked traders hold it or sold it and their pnl on it, and their theses.

NameTypeReqDescription
addressstringyes–
chainstringyeschain id as the tools give it

No output schema declared.

No examples provided.

get_trader ~81

a trader's copy.top profile (fomo or pump.fun): pnl 30d (realized, unrealized, total), roi, win rate, fair play verdict and badges, followers, copiers, platforms, largest open positions, latest trades and theses.

NameTypeReqDescription
handlestringyesthe trader's handle, as search or another tool gave it

No output schema declared.

No examples provided.

hl_get_calls ~46

x analysts ranked by the track record of their calls on one hyperliquid market, and their recent calls.

NameTypeReqDescription
coinstringyese.g. BTC, ETH, SOL

No output schema declared.

No examples provided.

hl_get_market_read ~81

copy.top's read of one major hyperliquid market: technicals (rsi, emas, trend), funding vs its history and other venues, premium, open interest changes, what the top 300 traders hold and their latest moves, nearby liquidations, fear and greed.

NameTypeReqDescription
coinstringyese.g. BTC, ETH, SOL

No output schema declared.

No examples provided.

hl_get_markets ~93

live hyperliquid markets (crypto perps and hip-3: stocks, indices, commodities, fx): mark price, 24h change, 24h volume, open interest, hourly funding, max leverage. optional category; sorted by 24h volume.

NameTypeReqDescription
categorystring–e.g. crypto, stocks, indices, commodities, fx
limitinteger–default 20

No output schema declared.

No examples provided.

hl_get_trader ~70

a hyperliquid trader by address: profile and metrics (win rate, profit factor, drawdown, usual leverage, score), pnl per window, open positions with entry, size, leverage and liquidation price, and latest fills.

NameTypeReqDescription
addressstringyes0x + 40 hex

No output schema declared.

No examples provided.

hl_get_traders ~101

rank hyperliquid perps traders tracked by copy.top. window 24h, 7d, 30d or all; sort pnl or roi. each row: address, name, account value, pnl, roi, volume, win rate, style, trades per day, max drawdown 30d, top coins.

NameTypeReqDescription
limitinteger–default 10
sortstringyes–
windowstringyes–

No output schema declared.

No examples provided.

search ~51

find traders and coins on copy.top by name, handle, @x, $ticker or address. use it to resolve a name before the other tools.

NameTypeReqDescription
querystringyes2 to 80 characters

No output schema declared.

No examples provided.

Install

How do I install the copy.top MCP server?

copy.top is a hosted endpoint at https://copy.top/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · copy.top

# add to Claude Code
claude mcp add --transport http top-copy-mcp 'https://copy.top/mcp'
Common questions

What is the copy.top MCP server?

copy.top is an MCP server listed in the public MCP registry as top.copy/mcp. Live signals, trader intel and alerts from top fomo, pump.fun and hyperliquid traders. Read-only. This page covers its hosted endpoint (https://copy.top/mcp).

Is the copy.top MCP server safe to use?

copy.top scores 75 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the copy.top MCP server expose?

copy.top exposes 16 tools: search, get_trader, get_leaderboard, get_token, get_theses, and 11 more. Their descriptions and schemas cost roughly 1,465 tokens of context every time the server is loaded.

Does the copy.top MCP server require authentication?

No. We connected to copy.top without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the copy.top MCP server still maintained?

copy.top is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the copy.top MCP server?

VerifyMCP ran 13 checks on copy.top, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.