Fan Token Intel is a remote MCP server that gives an AI agent 25 tools, among them tokenintel_briefing, tokenintel_capital_rotation, tokenintel_describe. It answers at https://mcp-production-f681.up.railway.app/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 19 October 2026, succeeded.
Fan-token intelligence for Chiliz Chain: prices, whale flows, match event impact. 22 read tools.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
tokenintel_briefing | All-in-one ECOSYSTEM briefing: market regime, active signals, anomalies, health matrix, sports calendar, and whale activity in one response. Use instead of calling 6+ tools sequentially. USE THIS for a market-wide overview. USE tokenintel_t Inputs: focus, timeframe |
tokenintel_capital_rotation | Cross-token capital flow analysis. Shows which fan tokens are gaining vs losing volume relative to their recent average. Detects rotation: when whales exit one token, where does the capital go? Inputs: hours, limit, min_volume_usd |
tokenintel_describe | Get the full input schema for a specific tool. Returns the JSON Schema (parameters, types, required fields, descriptions) needed to call the tool via tokenintel_invoke. Use tokenintel_discover first to find tool names. Inputs: tool_name |
tokenintel_dex_depth | Get DEX depth and slippage curves for fan token pools on Chiliz Chain. Computes constant-product (x*y=k) price impact at trade sizes [1%, 5%, 10%, 25%] of pool reserves. Useful for agents evaluating execution costs before trading. Data from Inputs: token |
tokenintel_dex_liquidity | Get on-chain DEX liquidity data for fan tokens on Chiliz Chain. Returns pool TVL, depth, token reserves, and estimated slippage. Critical for agents that want to understand execution costs before trading on-chain. Inputs: token, limit |
tokenintel_discover | Discover available tools on the Fan Token Intel MCP server. Returns tool names and one-line descriptions, organized by category. Call with no arguments for all categories, or specify a category to filter. Categories: market_data, signals, s Inputs: category |
tokenintel_event_reaction_profile | Event-conditioned, market-adjusted (vs CHZ) token reaction profiles for football events — by event_type x event_side(for/against) x minute x scoreline_state x importance. Returns mean/median abnormal return, match-clustered t-stat, bootstra Inputs: event_type, event_side, minute_bucket, scoreline_state, importance, horizon_min |
tokenintel_goal_direction_asymmetry | THE event-impact moat: how a fan token reacts when its team SCORES vs CONCEDES a goal, market-adjusted vs CHZ at +15/+30/+60m. The blended 'all goals' number hides the real signal — scoring is ~priced-in, conceding moves price. Returns the Inputs: minute_bucket |
tokenintel_governance_validators | List active validators on Chiliz Chain governance. Shows validator addresses and total CHZ delegated to each. Use this to find the best validator before staking. |
tokenintel_health_matrix | Get health grades (A-F) for all tracked fan tokens. Each token is scored across trading volume, order-book liquidity, spread, holder distribution and price stability -- 5-pillar weighted: volume(25%) + liquidity(25%) + spread(20%) + holders Inputs: response_format |
tokenintel_invoke | Invoke any tool on the Fan Token Intel MCP server by name. Pass the tool_name and its arguments. The result is identical to calling the tool directly. Auth and rate limits apply as normal. Use tokenintel_describe to get the required argumen Inputs: tool_name, arguments |
tokenintel_late_game_redcard_profile | Red-card reaction profile (market-adjusted vs CHZ). Rare and high-impact: returns abnormal return at +15/+30/+60m with honest wide confidence intervals and sample size; flags cells with n<15. Descriptive history, not advice. Inputs: event_side, minute_bucket |
tokenintel_macro_context | Get current crypto macro context: BTC dominance, CHZ price, funding rates, fear & greed index, and risk environment assessment. |
tokenintel_market_regime | Get current market conditions — BTC trend, CHZ momentum, fear/greed index, and the platform's market regime classification. Useful for filtering or adjusting signal confidence based on macro conditions. |
tokenintel_match_correlation | Historical match-to-price correlation. Ask 'what happens to BAR after Champions League wins?' and get backtested data with price impact percentages. Returns individual match records with price at kickoff, fulltime, +1h, +24h and aggregate s Inputs: token, result_filter, competition_filter, venue_filter, limit |
tokenintel_match_event_replay | Event-by-event reaction tape for a single match: each goal/red card with its minute, running score, scoreline state, and the market-adjusted token reaction at +15/+30/+60m (plus pre-event drift). The non-reconstructable moat artifact. match Inputs: match_id, token, date |
tokenintel_match_impact_history | Historical match price impact data for a fan token. Returns price snapshots at -24h, kickoff, fulltime, +1h, +24h with returns for each match. Filter by result (win/loss/draw), competition, venue. WINDOWS: return_total_pct is measured price Inputs: token, result, days, limit |
tokenintel_match_odds | Prediction-market odds curve for a single match from the in-play odds tape (odds_ticks): per-market (home/draw/away) implied-probability series with source labels (polymarket = CLOB midpoint, apifootball = de-vigged bookmaker odds), pre-mat Inputs: match_id, token, date, include_settlement_ticks |
tokenintel_odds_coverage | Discover which matches have prediction-market odds coverage in the in-play odds tape (odds_ticks): per-match tick counts by source (polymarket = CLOB midpoint, apifootball = de-vigged bookmaker odds), in-play tick counts vs kickoff, capture Inputs: token, days_back, days_ahead |
tokenintel_price_candles | Historical OHLCV price candles for any fan token. Intervals: 1h, 4h, 1d. Up to 180 days lookback. Returns open, high, low, close, volume for each period. Use for backtesting, charting, trend analysis, or building your own signals. Inputs: token, interval, days, limit |
tokenintel_realtime_prices | Get the freshest available prices with staleness metadata. Returns price_age_seconds so agents know exactly how stale each price is. Lightweight and fast -- call this before any trade decision to get current prices. Supports multiple tokens Inputs: tokens |
tokenintel_register | Get a free Fan Token Intel API key, self-serve — no human in the loop. Provide a name, an email, and terms_accepted=true; the key (ti_live_...) comes back in the response along with your tier and rate limits. Free-tier keys unlock the read- Inputs: name, email, terms_accepted |
tokenintel_social_sentiment | Social sentiment for a fan token. The only live social source is the LunarCrush aggregated feed, and on the current plan it provides galaxy_score and alt_rank ONLY — sentiment and social_volume come back null (see lunarcrush.fields_unavaila Inputs: token, hours |
tokenintel_token_context | SINGLE-TOKEN deep dive: realtime price, CEX whale flow, on-chain Chiliz Chain (FanX) liquidity with slippage at 1%/5% of reserves, and upcoming matches for one symbol. The default tool to call before evaluating a trading decision on a speci Inputs: token |
tokenintel_whale_flows | Get real-time whale distribution data for a fan token. Shows the ratio of whale sells to total whale activity on CEX exchanges. sell_ratio = whale sell volume / total whale volume; the payload labels >0.65 'distribution' and <0.35 'accumula Inputs: token, timeframe_hours, exchange, min_trade_usd |
Every block below points at https://mcp-production-f681.up.railway.app/mcp. Pick your client and copy.
claude mcp add --transport http fan-token-intel https://mcp-production-f681.up.railway.app/mcp
{
"mcpServers": {
"fan-token-intel": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp-production-f681.up.railway.app/mcp"]
}
}
}{
"mcpServers": {
"fan-token-intel": {
"url": "https://mcp-production-f681.up.railway.app/mcp"
}
}
}{
"servers": {
"fan-token-intel": {
"type": "http",
"url": "https://mcp-production-f681.up.railway.app/mcp"
}
}
}{
"context_servers": {
"fan-token-intel": {
"url": "https://mcp-production-f681.up.railway.app/mcp"
}
}
}{
"mcpServers": {
"fan-token-intel": {
"serverUrl": "https://mcp-production-f681.up.railway.app/mcp"
}
}
}{
"mcpServers": {
"fan-token-intel": {
"url": "https://mcp-production-f681.up.railway.app/mcp"
}
}
}name: Fan Token Intel
version: 0.0.1
schema: v1
mcpServers:
- name: Fan Token Intel
type: streamable-http
url: https://mcp-production-f681.up.railway.app/mcp{
"mcpServers": {
"fan-token-intel": {
"httpUrl": "https://mcp-production-f681.up.railway.app/mcp"
}
}
}{
"mcpServers": {
"fan-token-intel": {
"type": "http",
"url": "https://mcp-production-f681.up.railway.app/mcp"
}
}
}{
"mcpServers": {
"fan-token-intel": {
"url": "https://mcp-production-f681.up.railway.app/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fmcp-production-f681.up.railway.app%2Fmcp&type=streamable_http&id=fan-token-intel&name=Fan%20Token%20Intel
It answered our last check on 19 October 2026 in 116 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
25, as returned by the server's own tools/list on 12 September 2026: tokenintel_briefing, tokenintel_capital_rotation, tokenintel_describe, tokenintel_dex_depth, tokenintel_dex_liquidity, tokenintel_discover, tokenintel_event_reaction_profile, tokenintel_goal_direction_asymmetry, and 17 more.
It answered our last check on 19 October 2026 in 116 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mcp-production-f681.up.railway.app/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.brunopessoa22. Endpoint host: mcp-production-f681.up.railway.app. ARD identifier: urn:air:io.github.brunopessoa22:mcp:fan-token-intel.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.