cabal-hunter-mcp 1.0.1 → 1.0.2

package/README.md

@@ -28,11 +28,11 @@ Your autonomous trading agent is reading rug.check scores, liquidity locks, and
 
 **None of that catches a cabal.**
 
-A cabal is 15 fresh wallets — all funded from the same master wallet, all buying in the first 90 seconds of launch — quietly accumulating 25-40% of supply before your bot sees the first candle. Contract clean. LP burned. Everything green.
+A handful of wallets take the bottom of a launch, the chart looks clean — contract fine, LP burned, everything green — and then they sell into whoever bought after them. You are the exit liquidity.
 
-Then they dump. Simultaneously. Into your liquidity.
+This template integrates **[Cabal-Hunter](https://api.cabal-hunter.com)** as a pre-trade safety check, so your agent can see who is holding and who has already positioned to sell before it signs a swap.
 
-This template integrates **[Cabal-Hunter](https://api.cabal-hunter.com)** — a live on-chain funding tracer — as a pre-trade safety check so your agent catches coordinated launches before it signs a swap.
+> **A note on what we do and don't claim.** This README used to open with "15 fresh wallets funded from the same master wallet, accumulating 25-40% of supply." We went looking for that pattern and could not find it. Tracing 323 pump.fun launches at the bonding curve turned up **zero coordinated funding clusters**, and showed why: the median launch has about **five successful buyers**, because on one representative token **1,260 of the curve's 1,266 transactions failed**. Launch capture is a sniper *race* between competing bots, not a quiet cabal. The detection layers below are the ones we can actually evidence — holder concentration, same-block bundles, coordinated selling and deployer history. The pre-launch funding tracer was withdrawn; the [full write-up is here](https://github.com/paulf280-ui/cabal-hunter-mcp#a-note-on-the-withdrawn-trace_funding-tool).
 
 ---
 
@@ -40,7 +40,7 @@ This template integrates **[Cabal-Hunter](https://api.cabal-hunter.com)** — a
 
 The classic pump.fun exit-liquidity setup: wallets positioned before the crowd take the bottom of a launch, then dump on the retail (and bots) that pile in after. Cabal-Hunter's headline output is a single **Exit-Liquidity Risk** verdict (`LOW | ELEVATED | HIGH`) that synthesises every signal below into the only thing that matters before you sign a swap: *are the insiders positioned to dump on you?*
 
-## What Cabal-Hunter Does — Seven Detection Layers
+## What Cabal-Hunter Does
 
 ```
 Token mint address
@@ -50,9 +50,14 @@ Token mint address
    rug dev) into LOW | ELEVATED | HIGH: are insiders set up to dump on
    a buyer? The one number a trading agent needs.
       ↓
-1. FUNDING TRACE — top holders walked back to launch: who was funded
-   by the same source wallet? (classic cabal signature). Every cluster
-   carries evidence_txs[] — the actual funding transactions on Solscan.
+1. HOLDER FUNDING LINEAGE — the CURRENT top holders walked back: were
+   they seeded by the same wallet? Only System-owned accounts count as
+   a funder, so pools, vaults and routers can never be mistaken for a
+   person (that mistake is exactly what got our pre-launch tracer
+   withdrawn). Every cluster carries evidence_txs[] — the actual
+   funding transactions on Solscan. This layer is genuinely rare to
+   fire; treat a hit as significant and its absence as no evidence
+   either way.
       ↓
 2. SAME-BLOCK BUNDLE DETECTION — holders whose token accounts were
    created in the EXACT same slot bought in one Jito bundle. Catches
@@ -165,7 +170,7 @@ Your agent will call `check_cabal_risk(mintAddress)` before any swap and abort i
 
 ### 4. Direct REST API
 
-For headless scripts, custom bots, or any language. **The first 100 calls/month are free — no key, no signup.** Just call it:
+For headless scripts, custom bots, or any language. **The first 250 calls/month are free — no key, no signup.** Just call it:
 
 ```bash
 curl "https://api.cabal-hunter.com/api/scan-cabal?mintAddress=YOUR_MINT_ADDRESS"
@@ -353,7 +358,7 @@ After that, pick whatever matches how hard your bot works (priced at cost — it
 
 Prepaid keys: send USDC once → `POST /api/buy-key` with the tx signature → use header `X-API-Key` on every scan. Or pay per-call via x402 (`X-Payment-Signature` header). No credit card, no account, no lock-in.
 
-**Does it pay for itself?** A bot sniping $1 positions loses ~$40/month to rugs it never saw coming — rugs are the #1 way snipers bleed money. Cabal-Hunter flags them _before_ the buy. Dodge just 9 and the Unlimited tier has already paid for itself; every rug after that is capital back in your pocket, redeployed into trades that can actually run.
+**Does it pay for itself?** Work it out with your own numbers rather than ours: the Unlimited tier is $9 a month, so it pays for itself the first time it keeps you out of a position bigger than $9 that goes to zero. Whether that happens once a month or once a week depends on what you trade and how often — we are not going to invent an average for you.
 
 Payment is native on Solana — no credit card, no account, no subscription lock-in.
 

package/demo/python_demo.py

@@ -2,8 +2,9 @@
 Cabal-Hunter API demo — Python
 Checks a Solana token for coordinated wallet clusters before buying.
 
-First 100 queries/month are FREE — no payment required.
-After that: $0.05 USDC per query via X-Payment-Signature header.
+First 250 scans/month are FREE — no signup, no API key, no payment.
+After that: $0.001 USDC per scan via X-Payment-Signature, or a prepaid
+key ($9/month unlimited, fair use 50k) via X-API-Key.
 
 Run:  python demo/python_demo.py
 """
@@ -20,7 +21,8 @@ DEMO_MINT = "Axpzs7FEMYzpcfqVcDjDMQb2rsgMYVJADNpUZe7bpump"
 def check_token(mint: str) -> dict:
     """
     Query Cabal-Hunter for a token.
-    Free for first 100 queries/month. After that, pass X-Payment-Signature.
+    Free for the first 250 scans/month. After that, pass X-Payment-Signature
+    or X-API-Key.
     """
     resp = requests.post(API, json={"mintAddress": mint}, timeout=30)
 
@@ -54,7 +56,7 @@ if __name__ == "__main__":
 
     free_left = report.get("free_queries_remaining")
     if free_left is not None:
-        print(f"✅ Free tier — {free_left} free queries remaining this month\n")
+        print(f"✅ Free tier — {free_left} free scans remaining this month\n")
 
     print(f"Token:       {report.get('token_name', '?')}")
     print(f"Risk:        {report.get('risk')}")

package/demo/typescript_demo.ts

@@ -2,8 +2,9 @@
  * Cabal-Hunter API demo — TypeScript/Node.js
  * Checks a Solana token for coordinated wallet clusters before buying.
  *
- * First 100 queries/month are FREE — no payment required.
- * After that: $0.05 USDC per query via X-Payment-Signature header.
+ * First 250 scans/month are FREE — no signup, no payment required.
+ * After that: $9/month unlimited, or $0.001 USDC per scan via x402
+ * (X-Payment-Signature header).
  *
  * Run:  npx tsx demo/typescript_demo.ts
  */
@@ -66,7 +67,7 @@ async function main() {
   if (!report) process.exit(1)
 
   if (report.free_queries_remaining !== undefined) {
-    console.log(`✅ Free tier — ${report.free_queries_remaining} free queries remaining this month\n`)
+    console.log(`✅ Free tier — ${report.free_queries_remaining} free scans remaining this month\n`)
   }
 
   console.log(`Token:       ${report.token_name}`)

package/example_bot.py

@@ -1,7 +1,8 @@
 """
 Example: Integrate Cabal-Hunter into a Solana trading bot.
 Checks for coordinated wallet clusters before executing any swap.
-Cost: $0.05 USDC per check. Pays for itself the first time it blocks a rug.
+Cost: 250 scans/month free, then $0.001 USDC per check (or $9/month
+unlimited). Pays for itself the first time it blocks a rug.
 """
 
 import requests

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "cabal-hunter-mcp",
-  "version": "1.0.1",
-  "description": "Local stdio MCP server for Cabal-Hunter — on-chain Solana token cabal & rug detection. Proxies to api.cabal-hunter.com.",
+  "version": "1.0.2",
+  "description": "MCP server for Cabal-Hunter \u2014 Solana token rug & cabal detection for AI agents. Wallet clusters, same-block bundles, deployer track record with peak market caps, honeypot and authority traps. 250 free scans/month, no signup.",
   "type": "module",
   "bin": {
     "cabal-hunter-mcp": "server/index.mjs"
@@ -24,5 +24,10 @@
     "trading",
     "model-context-protocol"
   ],
-  "license": "MIT"
+  "license": "MIT",
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/paulf280-ui/solana-safe-sniper-mcp-template.git"
+  },
+  "homepage": "https://api.cabal-hunter.com"
 }

package/server/index.mjs

@@ -10,9 +10,10 @@
  * pump-and-dump history) and live coordinated dumps on any Solana mint before it
  * signs a swap.
  *
- * Free tier: 100 scans/month. Beyond that, scans are $0.02 USDC via x402 on
- * Solana — when a scan needs payment the API returns HTTP 402 with the payment
- * instructions, which this tool surfaces to the caller.
+ * Free tier: 250 scans/month per IP, no signup. Beyond that it is $9/month
+ * unlimited (fair use), or $0.001 USDC per scan via x402 on Solana — when a
+ * scan needs payment the API returns HTTP 402 with the payment instructions,
+ * which this tool surfaces to the caller.
  *
  * Uses the low-level Server API + JSON-Schema tool definitions for maximum
  * compatibility across @modelcontextprotocol/sdk versions.