# io.github.parkyucheol-del/alphapipeline (remote · alphapipeline-eu.onrender.com)

Pay-per-call x402 data API for AI trading agents: Polymarket arbitrage, kimchi premium & more.

- Trust score: 76/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- remote · `alphapipeline-eu.onrender.com`: 76/100 (this document), [markdown](https://verifymcp.io/servers/parkyucheol-del-alphapipeline/alphapipeline-eu.md), [page](https://verifymcp.io/servers/parkyucheol-del-alphapipeline/alphapipeline-eu)

## Channel facts

- Endpoint: `https://alphapipeline-eu.onrender.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.0`

## 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 2026-09-20.

- **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**: 70/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2899 tokens (~207/item across 14 items; 14 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 40/100
  - Stability observed for 12 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 14 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the io.github.parkyucheol-del/alphapipeline MCP server?

io.github.parkyucheol-del/alphapipeline is a hosted endpoint at https://alphapipeline-eu.onrender.com/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 parkyucheol-del-alphapipeline 'https://alphapipeline-eu.onrender.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "parkyucheol-del-alphapipeline": {
      "url": "https://alphapipeline-eu.onrender.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "parkyucheol-del-alphapipeline": {
      "type": "http",
      "url": "https://alphapipeline-eu.onrender.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.parkyucheol-del-alphapipeline]
url = "https://alphapipeline-eu.onrender.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "parkyucheol-del-alphapipeline": {
      "type": "remote",
      "url": "https://alphapipeline-eu.onrender.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add parkyucheol-del-alphapipeline --url 'https://alphapipeline-eu.onrender.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  parkyucheol-del-alphapipeline:
    url: "https://alphapipeline-eu.onrender.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "parkyucheol-del-alphapipeline": {
      "Transport": "http",
      "Url": "https://alphapipeline-eu.onrender.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add parkyucheol-del-alphapipeline -t streamable-http -u 'https://alphapipeline-eu.onrender.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "parkyucheol-del-alphapipeline": {
      "type": "http",
      "url": "https://alphapipeline-eu.onrender.com/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.

### 2026-09-20 (score 76, +1)

- [security] Tool “market.kimchi_alert” rewrote its description, which is the text the model reads

### 2026-09-19 (score 75, 0)

- [security] Tool “arb.spread_matrix” rewrote its description, which is the text the model reads
- [security] Tool “derivatives.funding_rate” rewrote its description, which is the text the model reads
- [security] Tool “derivatives.whale_position_audit” rewrote its description, which is the text the model reads
- [security] Tool “market.kimchi_alert” rewrote its description, which is the text the model reads
- [security] Tool “prediction.exit_capacity_audit” rewrote its description, which is the text the model reads
- [security] Tool “prediction.neg_risk_arbitrage” rewrote its description, which is the text the model reads
- [security] Tool “security.token_diagnostic” rewrote its description, which is the text the model reads
- [security] Tool “security.token_risk” rewrote its description, which is the text the model reads
- [security] Tool “unlocks.dump_risk” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 172 → 206

### 2026-09-17 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 74, +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.

### 2026-09-13 (score 73, +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.

### 2026-09-11 (score 72, +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.

### 2026-09-09 (score 71, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-09-08 (score 70)

First indexed and scored.

## MCP tools (14)

### `market.kimchi_alert` (~150 tokens)

Use this tool when evaluating Korean exchange price premiums, the 'kimchi premium', Upbit price gaps vs a global reference price, cross-border crypto arbitrage, or sudden Korea-specific price anomalies. Real-time Upbit vs Coinbase spot (CoinGecko fallback) - NOT a live Binance orderbook, despite the legacy binance_price_usdt field name kept for backward compatibility - with reverse-premium and surge alerts. Do not use for general USD spot prices or on-chain DEX swaps. Paid in USDC on Base (free while KIMCHI_ALERT_ENABLED=false).

Input parameters:

- `symbol` (string): Crypto ticker symbol to check, e.g. BTC, ETH, SOL. Defaults to BTC.

Output parameters:

- `alerts` (object)
- `binance_price_usdt` (number): Legacy field name kept for backward compatibility - NOT a live Binance price, see notice/cex_price_source.
- `cex_price_source` (string)
- `cex_reference_price_usdt` (number): Same value as binance_price_usdt under an honestly-named field.
- `generated_at` (object)
- `kimchi_premium_pct` (number)
- `notice` (string)
- `premium_change_1h_pct` (number)
- `symbol` (string)
- `thresholds` (object)
- `upbit_price_krw` (number)
- `usdkrw_rate_estimate` (number)

### `tools.ai_markdown` (~100 tokens)

Use this tool when an agent needs to parse clean webpage article content without wasting context tokens on ads, scripts, navigation, and HTML boilerplate, or when summarizing a specific URL. Converts any URL into clean Markdown optimized for LLM context windows. Do not use for raw API endpoints or binary files (PDF/images). Paid in USDC on Base.

Input parameters:

- `url` (string, required): Full http(s) URL of the webpage to convert to Markdown.

Output parameters:

- `char_count` (integer)
- `markdown` (string)
- `title` (string)
- `url` (string)

### `security.token_risk` (~211 tokens)

Use this tool before executing any on-chain swap to verify if an ERC-20 contract is a honeypot, rug-pull risk, or has malicious buy/sell taxes and mintability backdoors. GoPlus/Honeypot.is-backed security audit for a given contract address - beyond is_honeypot, also surfaces individual GoPlus risk signals (cannot_buy, cannot_sell_all, hidden_owner, transfer_pausable, selfdestruct, is_blacklisted, slippage_modifiable, owner_percent) into risk_flags, plus is_proxy/trading_cooldown as informational-only fields (not flagged, since both are common in legitimate contracts). All of these are null when the Honeypot.is fallback path is used. Do not use for market price discovery or liquidity depth. Paid in USDC on Base.

Input parameters:

- `chain_id` (integer, required): EVM chain id, e.g. 8453 for Base.
- `contract_address` (string, required): Token contract address (0x...).

Output parameters:

- `buy_tax_pct` (number|null)
- `cannot_buy` (boolean|null): GoPlus-only, null on Honeypot.is fallback. Feeds risk_flags.
- `cannot_sell_all` (boolean|null): GoPlus-only, null on Honeypot.is fallback. Feeds risk_flags.
- `chain_id` (integer)
- `contract_address` (string)
- `data_source` (string)
- `generated_at` (object)
- `hidden_owner` (boolean|null): GoPlus-only, null on Honeypot.is fallback. Feeds risk_flags.
- `holder_count` (integer|null)
- `is_blacklisted` (boolean|null): GoPlus-only, null on Honeypot.is fallback. Feeds risk_flags.
- `is_honeypot` (boolean|null)
- `is_in_dex` (boolean|null)
- `is_mintable` (boolean|null)
- `is_open_source` (boolean|null)
- `is_proxy` (boolean|null): GoPlus-only, null on Honeypot.is fallback. Informational only - does not feed risk_flags.
- `notice` (string|null)
- `owner_address` (string|null)
- `owner_percent` (number|null): Owner's % of total supply, GoPlus-only. Feeds 'high_owner_concentration' risk_flag at >=50%.
- `owner_renounced` (boolean|null)
- `risk_flags` (array)
- `risk_level` (string)
- `selfdestruct` (boolean|null): GoPlus-only, null on Honeypot.is fallback. Feeds risk_flags.
- `sell_tax_pct` (number|null)
- `slippage_modifiable` (boolean|null): GoPlus-only, null on Honeypot.is fallback. Feeds risk_flags.
- `token_name` (string|null)
- `token_symbol` (string|null)
- `trading_cooldown` (boolean|null): GoPlus-only, null on Honeypot.is fallback. Informational only - does not feed risk_flags.
- `transfer_pausable` (boolean|null): GoPlus-only, null on Honeypot.is fallback. Feeds risk_flags.

### `security.contract_health_audit` (~186 tokens)

Use this tool to check whether a token's liquidity pool is locked, burned, or freely held by a single wallet before trusting its liquidity - a rug-pull signal that security.token_risk does not cover. Reuses the same GoPlus data as token_risk (no extra upstream call) and rolls it up into a liquidity_health category (LOCKED/PARTIALLY_LOCKED/UNLOCKED/NO_LP_DATA). Does not include any qualitative 'suspicious transaction' judgment - only GoPlus's own lock/burn numbers. Do not use for honeypot or tax checks (use security.token_risk) or market price data. Paid in USDC on Base.

Input parameters:

- `chain_id` (integer, required): EVM chain id, e.g. 8453 for Base.
- `contract_address` (string, required): Token contract address (0x...).

Output parameters:

- `chain_id` (integer)
- `contract_address` (string)
- `data_source` (string)
- `generated_at` (object)
- `liquidity_health` (string)
- `lp_burned_pct` (number|null)
- `lp_holder_count` (integer|null)
- `lp_locked_pct` (number|null)
- `lp_total_supply` (number|null)
- `notice` (string|null)
- `risk_flags` (array)
- `token_name` (string|null)
- `token_symbol` (string|null)
- `top_unlocked_holder_pct` (number|null)

### `security.token_diagnostic` (~180 tokens)

Use this tool right before buying or swapping an unfamiliar token when you need a single-call combined security check: runs security.token_risk and security.contract_health_audit in parallel against the same GoPlus data and returns both, plus a deduped union of risk_flags and a plain risk_flags_count. Deliberately does not compute a composite score or letter grade - every field is copied unchanged from the two underlying tools. Cheaper than calling both separately. Do not use for token unlock/vesting risk (use unlocks.dump_risk) or if you only need one of the two checks (call that tool directly and pay less). Paid in USDC on Base.

Input parameters:

- `chain_id` (integer, required): EVM chain id, e.g. 8453 for Base.
- `contract_address` (string, required): Token contract address (0x...).

Output parameters:

- `buy_tax_pct` (number|null)
- `chain_id` (integer)
- `checks_completed` (integer)
- `checks_total` (integer)
- `contract_address` (string)
- `data_sources` (array)
- `generated_at` (object)
- `holder_count` (integer|null)
- `is_honeypot` (boolean|null)
- `is_mintable` (boolean|null)
- `is_open_source` (boolean|null)
- `liquidity_health` (string)
- `lp_burned_pct` (number|null)
- `lp_locked_pct` (number|null)
- `notice` (string|null)
- `owner_renounced` (boolean|null)
- `risk_flags` (array)
- `risk_flags_count` (integer)
- `sell_tax_pct` (number|null)
- `token_name` (string|null)
- `token_symbol` (string|null)
- `top_unlocked_holder_pct` (number|null)

### `derivatives.funding_rate` (~120 tokens)

Use this tool when analyzing perpetual futures funding rates, long/short market sentiment crowding, or timing hedging strategies before settlement periods. Aggregates Bybit (primary) and Binance (fallback) perpetual funding rates, plus mark_price/index_price (both paths) and open_interest_usd (Bybit path only - null on the Binance fallback). Do not use for spot market volume or token security checks. Paid in USDC on Base.

Input parameters:

- `symbol` (string, required): Ticker symbol, e.g. BTC, ETH, or BTCUSDT.

Output parameters:

- `data_source` (string)
- `funding_interval_hours` (integer|null)
- `funding_rate` (number|null)
- `funding_rate_percentage` (number|null)
- `generated_at` (object)
- `index_price` (number|null): Underlying spot index price feeding the perpetual's funding calculation. Populated on both the Bybit and Binance paths.
- `mark_price` (number|null): Perpetual futures mark price at lookup time. Populated on both the Bybit and Binance paths.
- `next_funding_time`
- `notice` (string|null)
- `open_interest_usd` (number|null): Total open interest in USD notional. Only available via the Bybit path - always null on the Binance fallback, since Binance's premiumIndex endpoint does not report open interest.
- `predicted_rate` (number|null)
- `symbol` (string)

### `derivatives.funding_apr_matrix` (~169 tokens)

Use this tool to evaluate a spot+perpetual carry trade: annualizes the current perpetual funding rate into an APR, flags which side (SHORT or LONG perp) currently collects funding, and computes how many days of that funding income it takes to recoup an assumed round-trip trading cost. Pure calculation on top of funding_rate data - no extra upstream call. Do not use for the raw current funding rate alone (use derivatives.funding_rate) or for spot price data. Paid in USDC on Base.

Input parameters:

- `assumed_round_trip_cost_pct` (number): Combined entry+exit trading fee percentage across both the spot and perpetual legs. Defaults to 0.2.
- `symbol` (string, required): Ticker symbol, e.g. BTC, ETH, or BTCUSDT.

Output parameters:

- `annualized_rate_pct` (number|null)
- `assumed_round_trip_cost_pct` (number)
- `breakeven_days` (number|null)
- `daily_funding_income_pct` (number|null)
- `data_source` (string)
- `funding_collector_side` (string|null)
- `funding_interval_hours` (integer|null)
- `funding_rate_percentage` (number|null)
- `generated_at` (object)
- `notice` (string|null)
- `periods_per_year` (integer|null)
- `symbol` (string)

### `dex.liquidity_slippage` (~212 tokens)

Use this tool to calculate expected DEX price slippage, pool liquidity depth, and optimal routing before executing an on-chain token swap. GeckoTerminal-backed pool analytics with constant-product slippage estimation for the requested trade_size_usd, plus a slippage_tiers array with the same estimate at fixed $1,000/$5,000/$10,000 sizes so an agent can gauge depth at a glance without extra calls. Do not use for centralized exchange (CEX) orderbooks or contract risk analysis. Paid in USDC on Base.

Input parameters:

- `network` (string): GeckoTerminal network id, e.g. base, eth. Defaults to base.
- `pool_address` (string): Specific DEX pool contract address (optional if token_address is given).
- `token_address` (string): Token contract address - the most liquid pool is auto-selected (optional if pool_address is given).
- `trade_size_usd` (number, required): Hypothetical trade size in USD to estimate slippage for.

Output parameters:

- `assumed_gas_cost_usd` (number|null): Flat per-swap gas estimate for this network, not a live gas quote.
- `data_source` (string)
- `estimated_slippage_pct` (number|null)
- `generated_at` (object)
- `liquidity_usd` (number|null)
- `network` (string)
- `notice` (string|null)
- `pool_address` (string|null)
- `pool_fee_pct` (number|null): Swap fee tier of the selected pool, parsed from pool_name. Disclosed for reference only - not subtracted from the slippage estimate.
- `pool_name` (string|null)
- `price_impact_model` (string)
- `quote_token_is_stablecoin` (boolean|null): If false or null, this pool isn't USD-quoted - an extra hop is needed to reach USD, not accounted for in the slippage estimate.
- `quote_token_symbol` (string|null): Parsed from pool_name (e.g. 'USDC' from 'WETH / USDC 0.05%').
- `slippage_tiers` (array|null)
- `token_address` (string|null)
- `trade_size_usd` (number)
- `volume_24h_usd` (number|null)

### `arb.spread_matrix` (~287 tokens)

Use this tool before executing a cross-venue arbitrage trade to check whether a global reference price (Coinbase spot, CoinGecko fallback - not a specific exchange orderbook) and a DEX pool price diverge enough to be worth trading after an assumed flat gas cost. Returns gross/net spread percentages and an is_profitable boolean - note net_spread_pct does NOT subtract the DEX pool's own swap fee (see pool_fee_pct), CEX trading fees, or slippage, so a spread that clears the threshold before those costs may not clear it after. Do not use for DEX-only liquidity depth checks or contract security. Paid in USDC on Base.

Input parameters:

- `min_spread_threshold_pct` (number): Net spread threshold (%) above which is_profitable is true. Defaults to 0.8.
- `network` (string): GeckoTerminal network id, e.g. base, eth. Defaults to base.
- `pool_address` (string): Specific DEX pool contract address (optional if token_address is given).
- `symbol` (string, required): Ticker symbol, e.g. SUI, BTC, ETH.
- `token_address` (string): Token contract address - the most liquid pool is auto-selected (optional if pool_address is given).
- `trade_size_usd` (number): Hypothetical trade size in USD. Defaults to 1000.

Output parameters:

- `assumed_gas_cost_usd` (number)
- `cex_price_usd` (number|null)
- `data_source` (string)
- `dex_price_usd` (number|null)
- `direction` (string|null)
- `generated_at` (object)
- `gross_spread_pct` (number|null)
- `is_profitable` (boolean)
- `min_spread_threshold_pct` (number)
- `net_spread_pct` (number|null)
- `network` (string)
- `notice` (string|null)
- `pool_address` (string|null)
- `pool_fee_pct` (number|null): DEX pool's fee tier (e.g. 0.05 for 0.05%), parsed from the pool name. Informational only - net_spread_pct does not subtract it.
- `status_message` (string)
- `symbol` (string)
- `trade_size_usd` (number)

### `derivatives.whale_position_audit` (~190 tokens)

Use this tool to audit a Hyperliquid wallet address you already know: every open perpetual position with side, size, leverage, max_leverage, unrealized PnL, return_on_equity_pct, liquidation price, and distance-to-liquidation percentage (max_leverage and return_on_equity_pct are Hyperliquid's own reported fields, not derived by this tool). This does not discover or rank 'smart money' wallets - Hyperliquid's public API has no leaderboard or large-trader disclosure endpoint, so it only audits an address you supply. risk_flags (HIGH_LEVERAGE, NEAR_LIQUIDATION) come from fixed numeric thresholds only. Do not use for spot price data or any exchange other than Hyperliquid. Paid in USDC on Base.

Input parameters:

- `address` (string, required): Hyperliquid/EVM wallet address to audit (0x...).

Output parameters:

- `account_value_usd` (number|null)
- `data_source` (string)
- `generated_at` (object)
- `margin_usage_pct` (number|null)
- `notice` (string|null)
- `open_position_count` (integer)
- `positions` (array)
- `risk_flags` (array)
- `total_margin_used_usd` (number|null)
- `total_notional_position_usd` (number|null)
- `wallet_address` (string)
- `withdrawable_usd` (number|null)

### `calendar.macro_dday` (~92 tokens)

Use this tool when an agent plans trading schedules around major US macroeconomic volatility, specifically days remaining until FOMC rate decisions, CPI prints, or NFP jobs reports. Zero-dependency static 2026 macro calendar with 100% uptime and no upstream failure risk. Do not use for real-time market price data or economic forecast consensus figures. No input parameters. Paid in USDC on Base.

Output parameters:

- `d_day` (integer|null)
- `data_source` (string)
- `description` (string|null)
- `event_datetime`
- `event_name` (string|null)
- `event_type` (string|null)
- `generated_at` (object)
- `impact_level` (string|null)
- `notice` (string|null)
- `tags` (array)
- `time_remaining`
- `upcoming_events` (array)

### `prediction.neg_risk_arbitrage` (~315 tokens)

Detect basket arbitrage in a Polymarket neg-risk (mutually-exclusive, multi-outcome) event - a full YES basket across all outcomes always settles to exactly $1, so a basket price away from $1 (after costs) is a near risk-free edge. Also returns buy/sell_basket_capacity_shares, the actual liquidity-bottleneck size executable right now, so this isn't just a top-of-book mirage - note *_capacity_notional_usd still prices that size at top-of-book (optimistic), so use *_capacity_vwap_notional_usd for the realistic fill cost. Also returns oldest_book_snapshot_time, the staleness bottleneck across all legs. Polymarket only. Do not use for binary Yes/No markets (no basket to arbitrage) or for Kalshi (its Data ToS forbids this use). Paid in USDC on Base.

Input parameters:

- `assumed_round_trip_cost_pct` (number): Gas + fees + slippage buffer, as a percentage of $1 basket notional. Defaults to 1.5.
- `event_slug` (string, required): Polymarket event slug, from the event's URL on polymarket.com.
- `max_slippage_pct` (number): How far past each leg's best price to walk the book when sizing capacity. Defaults to 1.0.
- `min_net_edge_pct` (number): Minimum net edge (%) required to flag arbitrage_viable: true. Defaults to 1.0.

Output parameters:

- `arbitrage_viable` (boolean)
- `assumed_round_trip_cost_pct` (number)
- `basket_ask_sum` (number|null)
- `basket_bid_sum` (number|null)
- `buy_basket_capacity_notional_usd` (number|null)
- `buy_basket_capacity_shares` (number)
- `buy_basket_capacity_vwap_notional_usd` (number|null): Volume-weighted price of filling buy_basket_capacity_shares by walking the order book depth, instead of pricing it at top-of-book like buy_basket_capacity_notional_usd does - more realistic actual fi…
- `buy_basket_gross_edge_usd` (number|null)
- `buy_basket_net_edge_usd` (number|null)
- `data_source` (string)
- `event_slug` (string)
- `generated_at` (object)
- `notice` (string|null)
- `num_outcomes` (integer)
- `oldest_book_snapshot_time`: The oldest of each leg's own order-book snapshot timestamp - the staleness bottleneck across all legs, since the whole basket calculation is only as fresh as its stalest leg. Null if no leg reported…
- `opportunity` (string)
- `sell_basket_capacity_notional_usd` (number|null)
- `sell_basket_capacity_shares` (number)
- `sell_basket_capacity_vwap_notional_usd` (number|null)
- `sell_basket_gross_edge_usd` (number|null)
- `sell_basket_net_edge_usd` (number|null)

### `prediction.exit_capacity_audit` (~264 tokens)

Walk a single Polymarket outcome's live order book to determine how much of a given position size can actually be filled right now, at what average price, and with how much price impact versus the best quote - a live snapshot, not historical liquidity. Also returns book_snapshot_time (the book's own reported timestamp) and Polymarket's own tick_size/min_order_size for this market (null if the book response didn't include them). Accepts either a raw token_id or a market_slug (+ outcome) to resolve it automatically - exact slug only, no fuzzy keyword search. Do not use for multi-outcome basket arbitrage detection (use prediction.neg_risk_arbitrage instead). Paid in USDC on Base.

Input parameters:

- `market_slug` (string): Exact Polymarket market slug, used to resolve token_id automatically.
- `outcome` (string): "yes" (default) or "no" - which side to resolve when using market_slug.
- `position_size_shares` (number, required): Number of outcome shares to sell (or buy). Must be positive.
- `side` (string): "sell" (default) or "buy".
- `token_id` (string): The outcome's CLOB token_id / asset_id, if already known.

Output parameters:

- `avg_exit_price` (number|null)
- `best_quote` (number|null)
- `book_snapshot_time`: The order book's own reported snapshot timestamp, so you can judge how fresh this read is.
- `data_source` (string)
- `executable` (boolean)
- `generated_at` (object)
- `market_slug` (string|null)
- `max_executable_shares` (number)
- `min_order_size` (number|null): Polymarket's own reported minimum order size for this market. Null if the book response didn't include it.
- `notice` (string|null)
- `position_size_shares` (number)
- `price_impact_pct` (number|null)
- `side` (string)
- `tick_size` (number|null): Polymarket's own reported minimum price increment for this market. Null if the book response didn't include it.
- `token_id` (string)

### `unlocks.dump_risk` (~248 tokens)

Use this tool to evaluate token unlock/vesting supply overhang risk before taking mid-to-long term positions - returns tokens whose currently-locked or unlock-eligible supply exceeds a materiality threshold, each with a computed risk_level (LOW/MEDIUM/HIGH). Default data source (on-chain Sablier vesting, the current configuration - no DropsTab key set) does NOT classify VC/team vs. other holders (is_insider_vc_team is always null) and does NOT provide exact unlock timing (days_until_unlock is always null, timing_precision='pending_schema_verification') - it only reports the currently-locked supply ratio. It does report vesting_deposit_amount/vesting_withdrawn_amount (Sablier's own depositAmount/withdrawnAmount, aggregated across streams) and vesting_progress_pct (withdrawn/deposit * 100), showing how far along the vesting schedule already is. Treat a null value as 'unknown', never as 'no risk'. Always check the response's coverage_notice field. Do not use for intra-day slippage or real-time transaction simulation. Paid in USDC on Base (free while DUMP_RISK_ENABLED=false).

Output parameters:

- `count` (integer)
- `coverage_notice` (string|null)
- `data_source` (string|null)
- `generated_at` (object)
- `notice` (string|null)
- `protocols_scanned` (integer)
- `supply_pct_threshold` (number)
- `unlocks` (array)
- `window_days` (integer|null)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/parkyucheol-del-alphapipeline/alphapipeline-eu#diagnostics

## Score history

- 2026-09-20: 76
- 2026-09-19: 75
- 2026-09-18: 75
- 2026-09-17: 75
- 2026-09-16: 74
- 2026-09-15: 74
- 2026-09-14: 73
- 2026-09-13: 73
- 2026-09-12: 72
- 2026-09-11: 72
- 2026-09-10: 71
- 2026-09-09: 71
- 2026-09-08: 70

## Common questions

### What is the io.github.parkyucheol-del/alphapipeline MCP server?

io.github.parkyucheol-del/alphapipeline is an MCP server listed in the public MCP registry as io.github.parkyucheol-del/alphapipeline. Pay-per-call x402 data API for AI trading agents: Polymarket arbitrage, kimchi premium & more. This page covers its hosted endpoint (https://alphapipeline-eu.onrender.com/mcp).

### Is the io.github.parkyucheol-del/alphapipeline MCP server safe to use?

io.github.parkyucheol-del/alphapipeline scores 76 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 io.github.parkyucheol-del/alphapipeline MCP server expose?

io.github.parkyucheol-del/alphapipeline exposes 14 tools: market.kimchi_alert, tools.ai_markdown, security.token_risk, security.contract_health_audit, security.token_diagnostic, and 9 more. Their descriptions and schemas cost roughly 2,724 tokens of context every time the server is loaded.

### Does the io.github.parkyucheol-del/alphapipeline MCP server require authentication?

No. We connected to io.github.parkyucheol-del/alphapipeline without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the io.github.parkyucheol-del/alphapipeline MCP server still maintained?

io.github.parkyucheol-del/alphapipeline is still listed as active in the MCP registry. We last reached this channel on 20 September 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://alphapipeline-eu.onrender.com/mcp
- Repository: https://github.com/parkyucheol-del/alphapipeline
- Changelog RSS feed: https://verifymcp.io/servers/parkyucheol-del-alphapipeline/alphapipeline-eu.xml
- Changelog JSON feed: https://verifymcp.io/servers/parkyucheol-del-alphapipeline/alphapipeline-eu.json
- HTML version of this page: https://verifymcp.io/servers/parkyucheol-del-alphapipeline/alphapipeline-eu