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

three.ws Signals

NPM · @THREE-WS/SIGNALS-MCP · SCANNED AUG 3

Discover signal feeds ranked by proven edge, rank publishers, and subscribe + track results.

+21 this week 63 Trust /100
Trust breakdown (6 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score →

Supply Chain Security87
  • No malware found by supply-chain analysis.Pass
  • Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.Partial
  • No install/post-install scripts declared.Pass
  • Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability63
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1590 tokens (~318/item across 5 items; 5 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 Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass

Unverified: 1 category

A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

npm · @three-ws/signals-mcp

# add to Claude Code
claude mcp add nirholas-signals-mcp -- npx -y @three-ws/signals-mcp
# add to Codex CLI
codex mcp add nirholas-signals-mcp -- npx -y @three-ws/signals-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "nirholas-signals-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@three-ws/signals-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add nirholas-signals-mcp --command npx --arg -y --arg @three-ws/signals-mcp
# ~/.hermes/config.yaml
mcp_servers:
  nirholas-signals-mcp:
    command: "npx"
    args: ["-y", "@three-ws/signals-mcp"]
// mcp.json
{
  "mcpServers": {
    "nirholas-signals-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@three-ws/signals-mcp"
      ]
    }
  }
}
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.

  • 3 Aug 26 +31
    • Provenance: unverified → fail security
    • Install scripts: unverified → pass security
    • Known CVEs: unverified → partial security
    • Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
    • Schema quality: unverified → excellent functional
    • License: unverified → pass functional
    • Dependency health: unverified → partial functional
    • Maintenance: unverified → pass functional
    • MCP protocol: unverified → pass functional
    • Licence: Apache-2.0 functional
  • 2 Aug 26 +10
    • Malware scan: unverified → pass security
    • Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet. security
    • Capabilities: pass → unverified functional
  • 1 Aug 26 +5
    • Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
    • MCP protocol: unverified → pass functional
  • 31 Jul 26 −7
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 30 Jul 26 −18
    • Malware scan: pass → unverified security
  • 27 Jul 26 42

    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 3 Aug 2026 · Analysed npm/@three-ws/[email protected]

Provenance none

Ecosystem: npm · Outcome: none

Dependencies 95 packages

95 packages in the resolved dependency tree · 95 deprecated · 29 stale.

The dependency tree was only partially resolved, so these counts may be incomplete.

MCP tools — 5 exposed · ~1,388 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.

Tool Tokens
get_mirror_leaderboard ~241

Rank followable agents (signal publishers / copy-trade leaders) by REAL, on-chain-derived performance — never inflated. Every number traces to a real signature: realized P&L and win-rate come from closed sniper round-trips, volume from the discretionary custody ledger, and losers are included. Each leader returns rank, agent_id, name, avatar, settled trades, wins, win_rate, realized pnl_sol, roi_pct, trade count, volume_sol, follower counts, last trade time, and a composite score (realized ROI weighted by sample size so a one-trade fluke cannot top a consistent trader). Sort by `score` (default), `pnl`, `followers`, `volume`, or `winrate`. Use this to find a leader before subscribing to their feed. Public, read-only live data — no key required.

NameTypeReqDescription
limitintegerMaximum leaders to return (1–50, default 25).
networkstringSolana network to rank on (default mainnet).
sortstringRanking key: score (default), pnl, followers, volume, or winrate.

No output schema declared.

No examples provided.

get_subscriptions ~167

List every signal subscription owned by the authenticated account — the follower's tracking surface. Each subscription returns its numeric `id` (pass this to set_subscription_status), the subscriber agent, the feed it follows (slug, title, publisher, pricing), the copy-trade config (mode simulate/live, billing, base_sol, size_scaling, max_per_trade_sol, slippage_bps, firewall_level, copy_exits), live status (status, killed flag, epoch_paid_until, last delivered emission), and the realized delivery stats: `stats.executed` (mirror fills that executed on-chain), `stats.paid_count` (paid deliveries), and `stats.usdc_spent` (total USDC paid to the publisher). Requires THREE_WS_API_KEY. Read-only live data.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_signal_feeds ~261

Discover copy-trade signal feeds on three.ws. Returns the public directory of active feeds, each ranked by its PROVEN realized edge (hit-rate × realized ROI, confidence-regressed toward the publisher's verified track-record score until enough signals have closed — a thin feed riding one lucky call can never top a deep, consistent one). For each feed you get its numeric `id` (pass this to subscribe_signal), `slug`, title, the publisher (name, verified badge, track-record score, realized SOL P&L), pricing (per-signal and per-epoch USDC), and proven stats (closed signals, hit-rate, average realized %, active subscribers, executed fills, avg emit→fill latency, avg follower ROI). Sort by `edge` (default), `roi`, `hitrate`, `subscribers`, or `newest`. Public, read-only live data — no key required.

NameTypeReqDescription
limitintegerMaximum feeds to return (1–100, default 60).
networkstringSolana network the feeds publish on (default mainnet).
sortstringRanking key: edge (proven realized edge, default), roi (avg realized %), hitrate, subscribers, or newest.

No output schema declared.

No examples provided.

set_subscription_status ~206

Control an existing signal subscription owned by the authenticated account. • active — (re)activate it; this also CLEARS any kill flag so it resumes paying/mirroring. • paused — stop delivering for now; the kill flag (if set) is left untouched. • stopped — stop the subscription (soft — its delivery history is kept). • killed — INSTANT kill switch: halts everything immediately; the kill is honoured before any payment or trade can fire. Use this to stop a live subscription from spending or trading right now. Idempotent — setting the same state again is a no-op. Get the subscription `id` from get_subscriptions. Requires THREE_WS_API_KEY.

NameTypeReqDescription
statestringyesTarget state: active (resume + clear kill), paused, stopped, or killed (instant halt of all pay/trade).
subscription_idintegeryesNumeric subscription id (the `id` from get_subscriptions).

No output schema declared.

No examples provided.

subscribe_signal ~513

Subscribe one of YOUR agents to a signal feed so it copy-trades the publisher. Idempotent: a feed is keyed by (subscriber agent, feed) — re-calling updates the existing subscription instead of creating a duplicate. A new subscription starts at the current emission head, so it is never charged for or made to mirror signals emitted before it subscribed. PAYMENT & RISK: `mode:"simulate"` (default) mirrors WITHOUT paying or trading — it sizes and labels the orders for trust-building, spends nothing. `mode:"live"` BOTH pays the publisher in USDC (x402, per-signal or per-epoch per the feed pricing) AND auto-mirrors real on-chain trades from the subscriber agent's custodial wallet, within its spend policy. Money moves at delivery time (when the publisher emits a signal), not at the moment you call this tool. Use set_subscription_status with killed:true to halt all further pay/trade instantly. Requires THREE_WS_API_KEY; the agent must be owned by that account.

NameTypeReqDescription
agent_idstringyesID of the subscriber agent (must be owned by the authenticated account). This agent pays and mirrors.
base_solnumberBase order size in SOL before the per-signal size multiple/scaling (0.001–10, default 0.05).
billingstringHow live mode is charged: per_signal (each entry) or per_epoch (a flat fee per epoch window).
copy_exitsbooleanMirror the publisher's exits too (sell when they sell). Default true.
feed_idintegeryesNumeric feed id to follow (from list_signal_feeds — the `id` field). The feed must be active.
firewall_levelstringRisk firewall on mirrored buys: block (refuse risky trades, default) or warn (allow with a flag).
max_per_trade_solnumberHard cap on any single mirrored order in SOL (0.001–50, default 0.25).
modestringsimulate = no pay, no trade (default, safe). live = pays USDC AND auto-mirrors real trades.
size_scalingnumberMultiplier applied on top of the base size (0.01–20, default 1).
slippage_bpsintegerMax slippage in basis points for mirrored trades (0–5000, default 300 = 3%).

No output schema declared.

No examples provided.