# MAD Synapse · Bundle Forensics (remote · agent.maddegen.art)

Who is behind a launch: bundles, insiders, airdrops, serial devs. Solana pump.fun + 18 EVM chains.

- Trust score: 67/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-17

## Components

- remote · `agent.maddegen.art`: 67/100 (this document), [markdown](https://verifymcp.io/servers/art-maddegen-agent-synapse-forensics/hub-mcp-forensics.md), [page](https://verifymcp.io/servers/art-maddegen-agent-synapse-forensics/hub-mcp-forensics)

## Channel facts

- Endpoint: `https://agent.maddegen.art/hub/mcp/forensics`
- Transports: `streamable-http`
- Auth: `none`
- Version: `2.2.0`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-17.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 32/100
  - 0% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1953 tokens (~390/item across 5 items; 4 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the MAD Synapse · Bundle Forensics MCP server?

MAD Synapse · Bundle Forensics is a hosted endpoint at https://agent.maddegen.art/hub/mcp/forensics, 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.

### Claude

```bash
claude mcp add --transport http art-maddegen-agent-synapse-forensics 'https://agent.maddegen.art/hub/mcp/forensics'
```

### Cursor

```json
{
  "mcpServers": {
    "art-maddegen-agent-synapse-forensics": {
      "url": "https://agent.maddegen.art/hub/mcp/forensics"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "art-maddegen-agent-synapse-forensics": {
      "type": "http",
      "url": "https://agent.maddegen.art/hub/mcp/forensics"
    }
  }
}
```

### Codex

```toml
[mcp_servers.art-maddegen-agent-synapse-forensics]
url = "https://agent.maddegen.art/hub/mcp/forensics"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "art-maddegen-agent-synapse-forensics": {
      "type": "remote",
      "url": "https://agent.maddegen.art/hub/mcp/forensics",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add art-maddegen-agent-synapse-forensics --url 'https://agent.maddegen.art/hub/mcp/forensics' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  art-maddegen-agent-synapse-forensics:
    url: "https://agent.maddegen.art/hub/mcp/forensics"
```

### Netclaw

```json
{
  "McpServers": {
    "art-maddegen-agent-synapse-forensics": {
      "Transport": "http",
      "Url": "https://agent.maddegen.art/hub/mcp/forensics"
    }
  }
}
```

### Vellum

```bash
assistant mcp add art-maddegen-agent-synapse-forensics -t streamable-http -u 'https://agent.maddegen.art/hub/mcp/forensics'
```

### Other

```json
{
  "mcpServers": {
    "art-maddegen-agent-synapse-forensics": {
      "type": "http",
      "url": "https://agent.maddegen.art/hub/mcp/forensics"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-17 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-15 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-13 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-12 (score 64, +1)

- [functional improvement] Stability: unverified → 0.07

### 2026-10-10 (score 63)

First indexed and scored.

## MCP tools (4)

### `bundle_forensics` (~344 tokens)

Bundle forensics + rug guard

Who bundled a Solana pump.fun launch: every block-0 wallet labelled sniper bot / bundle / dev-linked, supply bought and still held, holders who got tokens by transfer, serial-dev check, top-10 concentration, RugCheck — plus a back-tested skip/pass verdict. The rug guard MAD snipers use before every buy. Skip rules were tested on 2,221 real caller calls (held-out: stop-outs 10%→5%, rugs 16%→11%): creator launched another coin in the prior 24 h; top-10 wallets >35%; block-0 wallets that also bundled this creator's earlier launches; block-0 buys >20% of supply. Extra flags: RugCheck danger risks, insider wallets >15%, and >10% held by wallets that never bought on the curve (tokens moved in by transfer, the layered-bundle pattern of launch tools like Proxima). "ok:true" means no red flags were found, not that the coin is safe. When to use: To see WHO bundled a launch and get the skip/pass rug guard MAD snipers use; for a scored launch verdict use launch_scan (on the MAD Synapse · Wallets & Risk server, https://agent.maddegen.art/hub/mcp/risk). Price: $0.003 per call (10 free/day; after that a payment-required result lists x402 options). Errors: returns isError with a message for invalid input or an upstream failure (not charged).

Input parameters:

- `mint` (string, required): Solana token mint (pump.fun launches get the full bundle view) Base58 Solana address, 32-44 chars.

Output parameters:

- `bundle` (object|null)
- `dev` (object|null)
- `holders` (object|null)
- `mint` (string|null)
- `ms` (number|null)
- `ok` (boolean|null)
- `reasons` (array)
- `rugcheck` (object|null)
- `swap_url`
- `verdict` (string|null)
- `warn` (array)

### `bundler_profile` (~296 tokens)

Bundler wallet profile

Is this Solana wallet a bundler? Every pump.fun launch it bought in the first 2 slots over the last 10 days, which creators it keeps bundling for, and whether it is a mass sniper bot or a dev's private bundle wallet. From our block-0 registry of every pump.fun launch (non-creator buys in slots 0–1 after creation). kind: "sniper bot" (≥50 launches in 7 days, buys everything), "dev wallet" (most of its block-0 buys are on one or two creators' coins — a private bundle wallet), "bundler", or "not seen". Use it on wallets bundle_forensics lists, or on any wallet you are about to copy. When to use: To check one wallet from bundle_forensics (sniper bot vs a dev's private bundle wallet); for trading performance use pump_wallet (on the MAD Synapse · Pump & LP server, https://agent.maddegen.art/hub/mcp/pump). Price: $0.002 per call (10 free/day; after that a payment-required result lists x402 options). Errors: returns isError with a message for invalid input or an upstream failure (not charged).

Input parameters:

- `limit` (integer): Range 1-100. Default 25.
- `wallet` (string, required): Solana wallet. Base58 Solana address, 32-44 chars.

Output parameters:

- `block0_launches_10d` (number|null)
- `block0_launches_7d` (number|null)
- `distinct_creators` (number|null)
- `kind` (string|null)
- `own_launches_10d` (number|null)
- `recent` (array)
- `sol_spent_10d` (number|null)
- `top_creators` (array)
- `wallet` (string|null)
- `window` (string|null)

### `creator_launches` (~237 tokens)

Creator launch history + bundles

Every pump.fun coin a Solana wallet created in the last 10 days, how many graduated, and the wallets that bundle its launches again and again (its private bundle crew). Serial launchers (more than one coin a day) are the strongest rug signal in our tests: calls on coins whose creator launched another coin in the prior 24 h averaged −11% vs −5% after costs. Repeat block-0 wallets across a creator's launches are its own bundle wallets. When to use: For a dev's launch count and its repeat bundle crew; for graduation stats use pump_dev (on the MAD Synapse · Pump & LP server, https://agent.maddegen.art/hub/mcp/pump). Price: $0.002 per call (10 free/day; after that a payment-required result lists x402 options). Errors: returns isError with a message for invalid input or an upstream failure (not charged).

Input parameters:

- `creator` (string, required): creator (dev) wallet. Base58 Solana address, 32-44 chars.
- `limit` (integer): Range 1-100. Default 25.

Output parameters:

- `bundle_crew` (array)
- `creator` (string|null)
- `graduated` (number|null)
- `launches` (array)
- `launches_10d` (number|null)
- `launches_24h` (number|null)
- `serial` (boolean|null)
- `verdict` (string|null)

### `evm_bundle_forensics` (~575 tokens)

EVM launch + bundle forensics

Who bundled an EVM token launch (Base, BSC, Ethereum, Arbitrum, Robinhood and 13 more): creation-tx airdrops to fake holders, first-seconds buys, scripted fixed-cadence buying, fresh-wallet and transfer-only holders, dev holdings, exchange-labelled holders, GoPlus contract flags — plus a skip/pass verdict. Replays every ERC-20 Transfer of the token from its first mint on the public RPC, so for young tokens (Base ~4 days, BSC ~6 h of history in budget) holder balances, buys and wallet-to-wallet hand-offs are exact. Launchpads (Four.meme, Uniswap v4 PoolManager, v2/v3 pairs from Dexscreener) are detected; vault/locker contracts that never bought are kept out of the wallet rules, while contracts that DID buy (smart wallets, bundler contracts) count as wallets. Older tokens fall back to GoPlus holders with 527 exchange wallets named. Skip rules: GoPlus honeypot/tax>10%/owner powers; top-10 wallets >35%; first ~2 s of buys >20%; >10% held by wallets that never bought; creation tx airdropping ≥10 wallets or >10%; scripted buying (≥5 buys ≥1% at a regular cadence taking ≥15%); fresh wallets / buyer contracts >15%. Heuristic on EVM (mirrors the back-tested Solana guard); "pass" is not a safety promise. When to use: Bundles and who holds an EVM token launch (Base/BSC first-class); for contract-only flags use evm_token_security (on the MAD Synapse · Wallets & Risk server, https://agent.maddegen.art/hub/mcp/risk). Price: $0.005 per call (10 free/day; after that a payment-required result lists x402 options). Errors: returns isError with a message for invalid input or an upstream failure (not charged).

Input parameters:

- `chain` (string, required): EVM chain: ethereum, base, arbitrum, optimism, polygon, bsc, avalanche, linea, blast, scroll, gnosis, sonic, unichain, mantle, berachain, hyperevm, monad, robinhood. One of "ethereum", "base", "arbit…
- `token` (string, required): ERC-20 token contract address. 0x + 40 hex chars.

Output parameters:

- `bundle` (object|null)
- `chain` (string|null)
- `contract` (object|null)
- `holders` (object|null)
- `launch` (object|null)
- `ms` (number|null)
- `note` (string|null)
- `ok` (boolean|null)
- `pools` (array)
- `reasons` (array)
- `supply` (object|null)
- `symbol` (string|null)
- `token` (string|null)
- `transfers_replayed` (number|null)
- `verdict` (string|null)
- `warn` (array)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/art-maddegen-agent-synapse-forensics/hub-mcp-forensics#diagnostics

## Score history

- 2026-10-17: 67
- 2026-10-16: 66
- 2026-10-15: 66
- 2026-10-14: 65
- 2026-10-13: 65
- 2026-10-12: 64
- 2026-10-10: 63

## Common questions

### What is the MAD Synapse · Bundle Forensics MCP server?

MAD Synapse · Bundle Forensics is an MCP server listed in the public MCP registry as art.maddegen.agent/synapse-forensics. Who is behind a launch: bundles, insiders, airdrops, serial devs. Solana pump.fun + 18 EVM chains. This page covers its hosted endpoint (https://agent.maddegen.art/hub/mcp/forensics).

### Is the MAD Synapse · Bundle Forensics MCP server safe to use?

MAD Synapse · Bundle Forensics scores 67 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 MAD Synapse · Bundle Forensics MCP server expose?

MAD Synapse · Bundle Forensics exposes 4 tools: bundle_forensics, bundler_profile, creator_launches, evm_bundle_forensics. Their descriptions and schemas cost roughly 1,452 tokens of context every time the server is loaded.

### Does the MAD Synapse · Bundle Forensics MCP server require authentication?

No. We connected to MAD Synapse · Bundle Forensics without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the MAD Synapse · Bundle Forensics MCP server still maintained?

MAD Synapse · Bundle Forensics is still listed as active in the MCP registry. We last reached this channel on 17 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://agent.maddegen.art/hub/mcp/forensics
- Website: https://agent.maddegen.art/hub
- Changelog RSS feed: https://verifymcp.io/servers/art-maddegen-agent-synapse-forensics/hub-mcp-forensics.xml
- Changelog JSON feed: https://verifymcp.io/servers/art-maddegen-agent-synapse-forensics/hub-mcp-forensics.json
- HTML version of this page: https://verifymcp.io/servers/art-maddegen-agent-synapse-forensics/hub-mcp-forensics