# A.U.G.U.R Synapse (remote · augur-trade.com)

Solana + pump.fun intel for agents: launch verdicts, token risk, dev/wallet records, smart money.

- Trust score: 70/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

## Components

- remote · `augur-trade.com`: 70/100 (this document), [markdown](https://verifymcp.io/servers/art-maddegen-agent-synapse/hub-mcp-2.md), [page](https://verifymcp.io/servers/art-maddegen-agent-synapse/hub-mcp-2)

## Channel facts

- Endpoint: `https://augur-trade.com/hub/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `2.2.1`

## 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 2026-10-23.

- **Endpoint Security**: 80/100
  - 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.
  - The HSTS (Strict-Transport-Security) header is present.
  - 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**: 40/100
  - 0% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 3478 tokens (~217/item across 16 items; 15 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 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 15 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 17 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 A.U.G.U.R Synapse MCP server?

A.U.G.U.R Synapse is a hosted endpoint at https://augur-trade.com/hub/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.

### Claude

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

### Cursor

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

### VS Code

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

### Codex

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

### opencode

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

### OpenClaw

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

### Hermes

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

### Netclaw

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

### Vellum

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

### Other

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

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.

### 2026-10-23 (score 70, +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.

### 2026-10-21 (score 69, +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.

### 2026-10-19 (score 68, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-18 (score 67)

First indexed and scored.

## MCP tools (15)

### `launch_scan` (~194 tokens)

Launch scan (bundle)

One call, one verdict on a pump.fun launch: 0-100 score with positives and risks, graduation odds, dev record, snipers, holders, flow. Runs pump_token + pump_dev + pump_odds together (cheaper than calling them separately) and folds them into a single score and verdict an agent can act on: strong / neutral / weak / avoid. When to use: The one-call verdict on a pump.fun launch; it combines pump_token (callable here by name), pump_dev, pump_odds (callable here by name) and token_risk signals. Price: $0.025 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): pump.fun token mint. Base58 Solana address, 32-44 chars.

Output parameters:

- `curve` (object|null)
- `dev` (object|null)
- `flags` (array)
- `flow` (object|null)
- `graduation` (object|null)
- `launch_snipers` (object|null)
- `mint` (string|null)
- `note` (string|null)
- `positives` (array)
- `risks` (array)
- `score` (number|null)
- `swap_url`
- `symbol` (string|null)
- `top_curve_holders` (array)
- `verdict` (string|null)

### `token_risk` (~254 tokens)

Token risk score

0-100 rug-risk score for any Solana token: mint/freeze authority, Token-2022 traps, holder concentration, liquidity depth — plus pump.fun curve flags. Contract state is read live from Solana (authorities, Token-2022 extensions such as transfer fees, hooks, permanent delegate, pausable), holders from the largest accounts, market from DexScreener; for tokens still on any launchpad bonding curve (pump.fun, Meteora DBC, letsbonk…) liquidity is the SOL/USDC in the curve, read from chain (field `curve`). For pump.fun mints the curve forensics flags are merged in. When to use: For any Solana token, pump.fun or not. For pump.fun curve-stage detail use pump_token (callable here by name); for EVM tokens use evm_token_security (callable here by name). 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:

- `mint` (string, required): token mint. Base58 Solana address, 32-44 chars.

Output parameters:

- `dex` (string|null)
- `disclaimer` (string|null)
- `fdv_usd` (number|null)
- `flags` (array)
- `found` (boolean|null)
- `generated_utc` (string|null)
- `grade` (string|null)
- `known_asset` (object|null)
- `liquidity_total_usd` (number|null)
- `liquidity_usd` (number|null)
- `mint` (string|null)
- `name` (string|null)
- `onchain` (object|null)
- `onchain_error`
- `pair_age_hours` (number|null)
- `pair_url` (string|null)
- `price_usd` (string|null)
- `score` (number|null)
- `solana_pairs` (number|null)
- `swap_url` (string|null)
- `symbol` (string|null)
- `txns_24h` (object|null)
- `volume_24h_usd` (number|null)

### `pump_launches` (~182 tokens)

Newest pump.fun launches

The newest pump.fun tokens with dev buy, early buyers/volume, curve progress, market cap and creator launch count. Returns up to 50 of the most recent launches (seconds old) with the first-N-seconds flow already aggregated, so an agent can shortlist without replaying the chain. When to use: To discover new mints; then use launch_scan for a verdict on one of them. 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): How many of the newest launches to return. Range 1-50. Default 20.
- `window_s` (integer): early-flow window after creation. Range 30-3600. Default 300.

Output parameters:

- `launches` (array)
- `window_s` (number|null)

### `pump_pulse` (~114 tokens)

pump.fun market pulse

Live pump.fun heartbeat: trades/min, launches, graduations, graduation rate, hottest tokens in the last 15 min. Computed from our own live recording of every pump.fun bonding-curve trade. Use it to decide whether the launch market is hot or dead before scanning individual tokens. When to use: For the market right now; for trends over days use pump_history (callable here by name). Price: free. Errors: returns isError with a message for invalid input or an upstream failure (not charged).

Output parameters:

- `as_of` (string|null)
- `coverage` (string|null)
- `hottest_15m` (array)
- `last_24h` (object|null)
- `last_hour` (object|null)
- `recent_graduations` (array)
- `sol_usd` (number|null)
- `trades_per_min` (number|null)

### `pump_dev` (~160 tokens)

pump.fun dev track record

A creator wallet's launch history: launches, graduation rate, launch cadence, how fast the dev sells, verdict. Looks up every token the wallet created since recording began and replays the dev's own trades on its 15 most recent launches. When to use: For the creator of a token; pass the dev wallet, not the mint (pump_token (callable here by name) reports the dev of a mint). Price: $0.01 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.

Output parameters:

- `baseline` (string|null)
- `creator` (string|null)
- `first_launch` (string|null)
- `found` (boolean|null)
- `graduated` (number|null)
- `graduation_rate_pct` (number|null)
- `last_launch` (string|null)
- `launches` (number|null)
- `launches_last_24h` (number|null)
- `median_gap_between_launches_s` (number|null)
- `recent_launches` (array)
- `verdict` (array)

### `pump_wallet` (~210 tokens)

pump.fun wallet profile

Any wallet's pump.fun trading record: realized PnL, win rate, hold time, frequency (bot or human), tokens it launched. Analyses up to the last 20,000 curve trades of the wallet. Use it to judge whether a wallet is smart money, a sniper bot, a serial dumper or a dev. When to use: For a trader's pump.fun performance. For a quick deal/no-deal verdict on any wallet use counterparty_check; to test whether copying it pays use copy_backtest. Price: $0.01 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): How many of the wallet's most recent recorded trades to analyse. Range 100-20000. Default 20000.
- `wallet` (string, required): wallet address. Base58 Solana address, 32-44 chars.

Output parameters:

- `activity` (object|null)
- `classification` (string|null)
- `closed_positions` (object|null)
- `created_tokens` (object|null)
- `found` (boolean|null)
- `label` (string|null)
- `note` (string|null)
- `recent_tokens` (array)
- `wallet` (string|null)
- `window` (object|null)

### `smart_money` (~264 tokens)

Smart money on pump.fun

The pump.fun wallets with the best realized PnL in the last 24 h — and the tokens those wallets are buying right now. Leaderboard of wallets by realized profit on fully-closed curve positions (min 8 closed, rebuilt every 30 min), sortable by PnL, win rate or ROI, plus a live feed of what the top 50 bought in the last N minutes, ranked by how many of them piled in. When to use: To find wallets worth watching; then copy_backtest to test copying one. Price: $0.02 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:

- `exclude_bots` (boolean): drop sub-20-second and high-frequency wallets. Default false.
- `limit` (integer): How many top wallets to return. Range 1-50. Default 20.
- `sort` (string): Rank by realized PnL in SOL ("pnl"), win rate ("win_rate") or return on SOL spent ("roi"). Default "pnl".
- `window_min` (integer): look-back for buying_now. Range 1-120. Default 15.

Output parameters:

- `buying_now` (object|null)
- `leaderboard_built_at` (string|null)
- `note` (string|null)
- `sort` (string|null)
- `wallets` (array)
- `window` (string|null)

### `copy_backtest` (~376 tokens)

Copy-trade backtest

Would copying this wallet have made money? Replays its pump.fun entries and exits 0–25 slots late on the recorded curve and shows where the edge dies. Takes the wallet's pump.fun positions over the last 1–14 days and simulates a copier that buys the same token and sells when the leader sells, arriving 0, 1, 2, 5, 10 or 25 slots (0–10 s) late. Fills use the bonding-curve reserves our tape recorded at that moment, including curve fees and the copy's own price impact. Returns PnL, win rate and ROI per latency, the leader's own median ROI for contrast, and a verdict: copyable, latency-sensitive (edge gone by N slots), or not copyable. A wallet that looks great on its own PnL often loses money for anyone who follows it. When to use: After pump_wallet or smart_money, to check copying survives realistic delay. Price: $0.03 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:

- `days` (integer): How many days of the wallet's history to replay. Range 1-14. Default 3.
- `exit` (string): sell on the leader's first sell, or once it has sold 90%. Default "first_sell".
- `max_positions` (integer): most recent positions to replay. Range 10-300. Default 150.
- `size_sol` (number): SOL per copied entry. Range 0.01-10. Default 0.1.
- `wallet` (string, required): leader wallet to copy. Base58 Solana address, 32-44 chars.

Output parameters:

- `biggest_at_2_slots` (array)
- `by_lag` (array)
- `fast_flips_pct` (number|null)
- `found` (boolean|null)
- `label`
- `leader_median_roi_pct` (number|null)
- `note` (string|null)
- `setup` (object|null)
- `verdict` (string|null)
- `wallet` (string|null)

### `counterparty_check` (~157 tokens)

Counterparty check

One-call verdict on a Solana wallet before you deal with it: serial token launcher, fast dumper, trading bot, or clean. Combines the wallet's pump.fun launch history (graduation rate, how fast it sells its own launches) with its trading profile into a risk level and reasons. When to use: Before sending to or trading with a Solana wallet; for full trade stats use pump_wallet. 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:

- `wallet` (string, required): wallet address. Base58 Solana address, 32-44 chars.

Output parameters:

- `launches` (object|null)
- `level` (string|null)
- `reasons` (array)
- `risk_score` (number|null)
- `scope` (string|null)
- `trading` (object|null)
- `wallet` (string|null)

### `dlmm_whales` (~150 tokens)

DLMM LP whales

Meteora DLMM liquidity providers ranked by measured on-chain edge: net USD, median multiple, win rate, hold time, size, recency. Produced by our own discovery engine, which decodes DLMM liquidity instructions across high-volume and high-yield pools every few hours and scores each wallet's completed round trips. These are the wallets our live copier watches. Price: $0.02 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): How many ranked LP wallets to return. Range 1-25. Default 10.

Output parameters:

- `generated_at` (string|null)
- `method` (string|null)
- `pools_scanned` (number|null)
- `whales` (array)

### `price` (~144 tokens)

Token prices

USD price, 24h change and liquidity for up to 100 Solana mints; flags illiquid (dead) tokens. Jupiter price data with a liquidity floor: anything under $1,000 of liquidity is flagged dead, because round-trip quotes on dead curves look fine and are not. When to use: For Solana mints by address; for majors or other chains by symbol use crypto_price (callable here by name). Price: free. Errors: returns isError with a message for invalid input or an upstream failure (not charged).

Input parameters:

- `mints` (array, required): Solana token mint addresses (base58) to price. 1-100 items.

Output parameters:

- `prices` (array)
- `source` (string|null)

### `wallet_holdings` (~145 tokens)

Wallet holdings

Everything a Solana wallet holds — SOL, SPL and Token-2022 tokens — valued in USD and sorted by value. Reads token accounts from both token programs and prices them in one pass. Empty accounts are counted as reclaimable rent. When to use: For Solana wallets; for EVM wallets use evm_address (callable here by name). 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:

- `wallet` (string, required): wallet address. Base58 Solana address, 32-44 chars.

Output parameters:

- `empty_accounts` (object|null)
- `sol` (number|null)
- `sol_usd` (number|null)
- `token_accounts` (number|null)
- `tokens` (array)
- `tokens_usd` (number|null)
- `total_usd` (number|null)
- `wallet` (string|null)

### `tx_explain` (~149 tokens)

Explain a transaction

Turns any Solana transaction signature into plain facts: status, fee, programs by name, SOL and token balance changes per owner, a one-line summary. Works for swaps, pump.fun trades, LP moves, transfers and failures (includes the error log lines). When to use: For Solana signatures; for 0x hashes use evm_tx (callable here by name). 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:

- `signature` (string, required): Solana transaction signature (base58, 64-90 chars).

Output parameters:

- `compute_units` (number|null)
- `error`
- `error_logs`
- `fee_sol` (number|null)
- `found` (boolean|null)
- `programs` (array)
- `signature` (string|null)
- `signers` (array)
- `slot` (number|null)
- `sol_changes` (array)
- `status` (string|null)
- `summary` (string|null)
- `time` (string|null)
- `token_changes` (array)

### `bundle_forensics` (~318 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. 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)

### `solana_network` (~109 tokens)

Solana network status

Solana right now: TPS (total and non-vote), slot and block height, epoch progress and ETA, priority-fee percentiles, cluster version. Read from mainnet RPC: recent performance samples, epoch info, prioritization fees. When to use: For Solana fees/TPS; for EVM and BTC fee costs use gas_now (callable here by name). Price: free. Errors: returns isError with a message for invalid input or an upstream failure (not charged).

Output parameters:

- `avg_slot_ms` (number|null)
- `block_height` (number|null)
- `epoch` (number|null)
- `epoch_ends_in_hours` (number|null)
- `epoch_progress_pct` (number|null)
- `priority_fee_micro_lamports_per_cu` (object|null)
- `slot` (number|null)
- `tps_non_vote` (number|null)
- `tps_total` (number|null)
- `version` (string|null)
- `window_minutes` (number|null)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/art-maddegen-agent-synapse/hub-mcp-2#diagnostics

## Score history

- 2026-10-23: 70
- 2026-10-22: 69
- 2026-10-21: 69
- 2026-10-20: 68
- 2026-10-19: 68
- 2026-10-18: 67

## Common questions

### What is the A.U.G.U.R Synapse MCP server?

A.U.G.U.R Synapse is an MCP server listed in the public MCP registry as art.maddegen.agent/synapse. Solana + pump.fun intel for agents: launch verdicts, token risk, dev/wallet records, smart money. This page covers its hosted endpoint (https://augur-trade.com/hub/mcp).

### Is the A.U.G.U.R Synapse MCP server safe to use?

A.U.G.U.R Synapse scores 70 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 A.U.G.U.R Synapse MCP server expose?

A.U.G.U.R Synapse exposes 15 tools: launch_scan, token_risk, pump_launches, pump_pulse, pump_dev, and 10 more. Their descriptions and schemas cost roughly 2,926 tokens of context every time the server is loaded.

### Does the A.U.G.U.R Synapse MCP server require authentication?

No. We connected to A.U.G.U.R Synapse without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the A.U.G.U.R Synapse MCP server still maintained?

A.U.G.U.R Synapse is still listed as active in the MCP registry. We last reached this channel on 23 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://augur-trade.com/hub/mcp
- Website: https://augur-trade.com/hub
- Changelog RSS feed: https://verifymcp.io/servers/art-maddegen-agent-synapse/hub-mcp-2.xml
- Changelog JSON feed: https://verifymcp.io/servers/art-maddegen-agent-synapse/hub-mcp-2.json
- HTML version of this page: https://verifymcp.io/servers/art-maddegen-agent-synapse/hub-mcp-2