Insider Radar

by mypocketsmells · remote · no sign-in to list tools · v1.1.0 · published by GitHub user mypocketsmells

Lab telemetry market: 25 x402 USDC-paid tools — leaderboard, KOL signals, outcomes, more.

Changes · 26

Compare Registry entry

27 tools: 26 change things and 1 only read.

Scanned Oct 21, 2026

Deletes or cancels0Claude Code: deny
Can't be undone0Claude Code: ask
Changes things26Claude Code: ask: see these tools
Only reads1Claude Code: allow: see these tools

1 check matched something in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http insider-radar https://insider-radar-agent.insider-radar-agent.workers.dev/mcp

Findings

Matches of fixed checks, with the text they matched.

1 warn

Warnsolscout_verdicts
The server marks "solscout_verdicts" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
Matched text
annotations: {"readOnlyHint":true}; The description's first verb is "copy": a word for a change.
What this check looks for

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

27 tools

Changes things 26Creates or changes something that can be changed back.Claude Code: ask

alertsRecent lab alerts (drawdowns, retirements, anomalies).No 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.
Description, as the server wrote it
Recent lab alerts (drawdowns, retirements, anomalies). Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.
Annotations the server declares
- readOnlyHint: true
alpha_trackDaily equity/PnL histories for the lab's edge-protected bots under stable anonymous handles — real performance, withheld identities; track any handle across snapshots.No 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.
Description, as the server wrote it
Daily equity/PnL histories for the lab's edge-protected bots under stable anonymous handles — real performance, withheld identities; track any handle across snapshots. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.
Annotations the server declares
- readOnlyHint: true
arenaFleet-wide arena summary of the paper-trading lab (bot counts, venues, aggregate equity).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it
Fleet-wide arena summary of the paper-trading lab (bot counts, venues, aggregate equity). Free teaser.
calibrationForecast calibration by venue/category — predicted vs realized.No 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.
Description, as the server wrote it
Forecast calibration by venue/category — predicted vs realized. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.
Annotations the server declares
- readOnlyHint: true
congress_tapeParsed House/Senate PTR trades: member, ticker, type, amounts, filing lag (last 1000).No 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.
Description, as the server wrote it
Parsed House/Senate PTR trades: member, ticker, type, amounts, filing lag (last 1000). Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.
Annotations the server declares
- readOnlyHint: true
creatorsPump.fun deployer index built forward by our launch listener: 900+ creator wallets with launch histories, venue-aware rug counts, first/last seen.No 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.
Description, as the server wrote it
Pump.fun deployer index built forward by our launch listener: 900+ creator wallets with launch histories, venue-aware rug counts, first/last seen. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.
Annotations the server declares
- readOnlyHint: true
crowdingExposure crowding: where the fleet's directional risk is concentrated.No 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.
Description, as the server wrote it
Exposure crowding: where the fleet's directional risk is concentrated. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.
Annotations the server declares
- readOnlyHint: true
divergencesCross-venue probability divergences (e.g.No 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.
Description, as the server wrote it
Cross-venue probability divergences (e.g. Kalshi vs Polymarket gaps). Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.
Annotations the server declares
- readOnlyHint: true
fleet_ledgerFleet-wide daily P&L ledger: totals, venue splits, per-day rows, tape reconciliation — the transparency companion to alpha_track.No 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.
Description, as the server wrote it
Fleet-wide daily P&L ledger: totals, venue splits, per-day rows, tape reconciliation — the transparency companion to alpha_track. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.
Annotations the server declares
- readOnlyHint: true
insider_plans10b5-1 plan detection per insider filing — was the buy pre-scheduled?No 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.
Description, as the server wrote it
10b5-1 plan detection per insider filing — was the buy pre-scheduled? Per-accession tags plus aggregate plan rates. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.
Annotations the server declares
- readOnlyHint: true
insider_tapeParsed SEC Form-4 insider buys, newest first: roles, titles, shares, price, value, disclosure lag (last 1000).No 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.
Description, as the server wrote it
Parsed SEC Form-4 insider buys, newest first: roles, titles, shares, price, value, disclosure lag (last 1000). Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.
Annotations the server declares
- readOnlyHint: true
kol_eventsNarrated detector event stream: meta-signals, distribution flips, known-rugger callouts (last 2000 events).No 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.
Description, as the server wrote it
Narrated detector event stream: meta-signals, distribution flips, known-rugger callouts (last 2000 events). Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.
Annotations the server declares
- readOnlyHint: true
kol_frothMemecoin froth gauge, current level plus full history: human buys/hour, danger share, distribution events, percentile.No 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.
Description, as the server wrote it
Memecoin froth gauge, current level plus full history: human buys/hour, danger share, distribution events, percentile. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.
Annotations the server declares
- readOnlyHint: true
kol_outcomesForward-marked signal outcomes WITH a matched control arm: rug rates, checkpoint returns (15m/1h/6h/24h) by risk level and confluence — honesty-graded.No 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.
Description, as the server wrote it
Forward-marked signal outcomes WITH a matched control arm: rug rates, checkpoint returns (15m/1h/6h/24h) by risk level and confluence — honesty-graded. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.
Annotations the server declares
- readOnlyHint: true
kol_signals_delayedSame KOL confluence feed as kol_signals_live with every row at least 45 minutes old — the evaluation tier.No 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.
Description, as the server wrote it
Same KOL confluence feed as kol_signals_live with every row at least 45 minutes old — the evaluation tier. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.
Annotations the server declares
- readOnlyHint: true
kol_signals_liveLive KOL confluence buy/exit signals (≤15 min old): distinct human buyers, strength, rug-risk callouts, momentum — the actionable tier.No 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.
Description, as the server wrote it
Live KOL confluence buy/exit signals (≤15 min old): distinct human buyers, strength, rug-risk callouts, momentum — the actionable tier. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.
Annotations the server declares
- readOnlyHint: true
kol_statsPer-wallet outcome statistics for ~300 tracked memecoin KOL wallets — our computed win rates and PnL distributions over observed trades.No 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.
Description, as the server wrote it
Per-wallet outcome statistics for ~300 tracked memecoin KOL wallets — our computed win rates and PnL distributions over observed trades. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.
Annotations the server declares
- readOnlyHint: true
leaderboardRanked bot leaderboard with eff_n and the luck-ceiling honesty note.No 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.
Description, as the server wrote it
Ranked bot leaderboard with eff_n and the luck-ceiling honesty note. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.
Annotations the server declares
- readOnlyHint: true
optimizerOptimizer status and recent parameter decisions.No 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.
Description, as the server wrote it
Optimizer status and recent parameter decisions. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.
Annotations the server declares
- readOnlyHint: true
research_packSeven research panels in one call: family correlation + effective-n, edge calibration, insider event study, regime joins, econ calendar, weekly digest, daily alpha cards.No 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.
Description, as the server wrote it
Seven research panels in one call: family correlation + effective-n, edge calibration, insider event study, regime joins, econ calendar, weekly digest, daily alpha cards. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.
Annotations the server declares
- readOnlyHint: true
signalsCurrent signal feed headlines from the lab's signal bus.No 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.
Description, as the server wrote it
Current signal feed headlines from the lab's signal bus. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.
Annotations the server declares
- readOnlyHint: true
smart_holdings13F institutional holdings rollup: top-held names, filer roster, per-ticker holder counts (top 300).No 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.
Description, as the server wrote it
13F institutional holdings rollup: top-held names, filer roster, per-ticker holder counts (top 300). Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.
Annotations the server declares
- readOnlyHint: true
snipe_outcomesLaunch-snipe paper ledger with a randomized control arm: detect latency, entry efficiency, checkpoint marks per snipe.No 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.
Description, as the server wrote it
Launch-snipe paper ledger with a randomized control arm: detect latency, entry efficiency, checkpoint marks per snipe. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.
Annotations the server declares
- readOnlyHint: true
sol_depthRecorded Kalshi SOL-market L2 depth (top-5 levels per side), previous-day and older only (T+1) — we recorded it live; Kalshi publishes no historical depth.No 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.
Description, as the server wrote it
Recorded Kalshi SOL-market L2 depth (top-5 levels per side), previous-day and older only (T+1) — we recorded it live; Kalshi publishes no historical depth. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.
Annotations the server declares
- readOnlyHint: true
solscout_verdictsCopy-gradeability verdicts for Solana memecoin wallets: composite scores, consistency, retirement calls (candidate lists withheld).1 finding
Why it is in this group
- The description's first verb is "copy": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
  The server marks "solscout_verdicts" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
  Matched text
  annotations: {"readOnlyHint":true}; The description's first verb is "copy": a word for a change.
  What this check looks for
Description, as the server wrote it
Copy-gradeability verdicts for Solana memecoin wallets: composite scores, consistency, retirement calls (candidate lists withheld). Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.
Annotations the server declares
- readOnlyHint: true
wire_clustersCross-source evidence clusters joining price anomalies to specific SEC filings (Form 4 accessions, URLs) — graded, windowed, cited.No 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.
Description, as the server wrote it
Cross-source evidence clusters joining price anomalies to specific SEC filings (Form 4 accessions, URLs) — graded, windowed, cited. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.
Annotations the server declares
- readOnlyHint: true

Only reads 1Looks things up and changes nothing.Claude Code: allow

radar_statusService status: snapshot freshness, product catalog with per-call prices, and the honesty disclaimer.No findings
Why it is in this group
- The name "radar_status" says "status": a word for reading.
Description, as the server wrote it
Service status: snapshot freshness, product catalog with per-call prices, and the honesty disclaimer. Free.

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.

Install

Pinned to version 1.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http insider-radar https://insider-radar-agent.insider-radar-agent.workers.dev/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json

{
  "permissions": {
    "allow": [
      "mcp__insider-radar__radar_status"
    ],
    "ask": [
      "mcp__insider-radar__arena",
      "mcp__insider-radar__leaderboard",
      "mcp__insider-radar__signals",
      "mcp__insider-radar__alerts",
      "mcp__insider-radar__calibration",
      "mcp__insider-radar__divergences",
      "mcp__insider-radar__crowding",
      "mcp__insider-radar__optimizer",
      "mcp__insider-radar__creators",
      "mcp__insider-radar__kol_stats",
      "mcp__insider-radar__alpha_track",
      "mcp__insider-radar__sol_depth",
      "mcp__insider-radar__kol_signals_live",
      "mcp__insider-radar__kol_outcomes",
      "mcp__insider-radar__snipe_outcomes",
      "mcp__insider-radar__wire_clusters",
      "mcp__insider-radar__solscout_verdicts",
      "mcp__insider-radar__insider_plans",
      "mcp__insider-radar__research_pack",
      "mcp__insider-radar__kol_events",
      "mcp__insider-radar__fleet_ledger",
      "mcp__insider-radar__kol_signals_delayed",
      "mcp__insider-radar__kol_froth",
      "mcp__insider-radar__smart_holdings",
      "mcp__insider-radar__insider_tape",
      "mcp__insider-radar__congress_tape"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as insider-radar. Review it before you use it.

Keep track

Get told when this server's tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/io.github.mypocketsmells/insider-radar/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Anlyon alternative

26 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

Compare with other servers for the same product.

Source: MCP Registry. Synced Oct 21, 2026, 18:42 UTC.

For agents: Markdown · JSON · report this listing