Falsifylab Alpha

by FalsifyLab

188 downloads

Not rated

GitHub

About

Live DeFi yield, HL vaults, SEC insider/8-K, macro tape, ETF flows, airdrops, Polymarket whales — 8 MCP tools fed by the same pipeline running a live trading bot fleet. Free tier (no signup) + Pro $19/mo.

Details

Author: FalsifyLab
Downloads: 188
Categories: Finance, Other

- Provides 7 built‑in tools covering DeFi, equities, and macro data
- top_yield_farms – last‑24h DeFi yield picks with realistic APY
- hl_vault_leaderboard – Hyperliquid vault leaderboard (NAV, returns, score)
- insider_buy_clusters – Form 4 cluster buys (3+ insiders same ticker)
- sec8k_material_today – material 8‑K filings filtered by item code
- etf_flow_today – US spot BTC + ETH ETF net flows
- polymarket_whale_positions – top whale wallets and active positions
- macro_tape – live snapshot of SPX, NDX, VIX, yields, FX, commodities, crypto
- Free tier (no key) offers cached last‑24h data with rate limits
- Pro tier ($19/mo) unlocks real‑time data, 90‑day history, and no rate limits

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below

Plugin Name Falsifylab Alpha

Command (node, npx, python, etc.)

Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "falsifylab alpha": {
            "falsifylab-alpha": {
                "command": "python",
                "args": [
                    "-m",
                    "falsifylab_alpha_mcp"
                ],
                "env": {
                    "FL_API_KEY": "fl_xxx"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "falsifylab alpha": {
            "falsifylab-alpha": {
                "command": "python",
                "args": [
                    "-m",
                    "falsifylab_alpha_mcp"
                ],
                "env": {
                    "FL_API_KEY": "fl_xxx"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "falsifylab alpha": {
            "falsifylab-alpha": {
                "command": "python",
                "args": [
                    "-m",
                    "falsifylab_alpha_mcp"
                ],
                "env": {
                    "FL_API_KEY": "fl_xxx"
                }
            }
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "falsifylab alpha": {
            "falsifylab-alpha": {
                "command": "python",
                "args": [
                    "-m",
                    "falsifylab_alpha_mcp"
                ],
                "env": {
                    "FL_API_KEY": "fl_xxx"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "falsifylab alpha": {
            "falsifylab-alpha": {
                "command": "python",
                "args": [
                    "-m",
                    "falsifylab_alpha_mcp"
                ],
                "env": {
                    "FL_API_KEY": "fl_xxx"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "falsifylab alpha": {
            "falsifylab-alpha": {
                "command": "python",
                "args": [
                    "-m",
                    "falsifylab_alpha_mcp"
                ],
                "env": {
                    "FL_API_KEY": "fl_xxx"
                }
            }
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "falsifylab alpha": {
            "falsifylab-alpha": {
                "command": "python",
                "args": [
                    "-m",
                    "falsifylab_alpha_mcp"
                ],
                "env": {
                    "FL_API_KEY": "fl_xxx"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "falsifylab alpha": {
            "falsifylab-alpha": {
                "command": "python",
                "args": [
                    "-m",
                    "falsifylab_alpha_mcp"
                ],
                "env": {
                    "FL_API_KEY": "fl_xxx"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "falsifylab alpha": {
            "falsifylab-alpha": {
                "command": "python",
                "args": [
                    "-m",
                    "falsifylab_alpha_mcp"
                ],
                "env": {
                    "FL_API_KEY": "fl_xxx"
                }
            }
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "falsifylab alpha": {
            "falsifylab-alpha": {
                "command": "python",
                "args": [
                    "-m",
                    "falsifylab_alpha_mcp"
                ],
                "env": {
                    "FL_API_KEY": "fl_xxx"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "falsifylab alpha": {
            "falsifylab-alpha": {
                "command": "python",
                "args": [
                    "-m",
                    "falsifylab_alpha_mcp"
                ],
                "env": {
                    "FL_API_KEY": "fl_xxx"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "falsifylab alpha": {
            "falsifylab-alpha": {
                "command": "python",
                "args": [
                    "-m",
                    "falsifylab_alpha_mcp"
                ],
                "env": {
                    "FL_API_KEY": "fl_xxx"
                }
            }
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "falsifylab alpha": {
            "falsifylab-alpha": {
                "command": "python",
                "args": [
                    "-m",
                    "falsifylab_alpha_mcp"
                ],
                "env": {
                    "FL_API_KEY": "fl_xxx"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "falsifylab alpha": {
            "falsifylab-alpha": {
                "command": "python",
                "args": [
                    "-m",
                    "falsifylab_alpha_mcp"
                ],
                "env": {
                    "FL_API_KEY": "fl_xxx"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "falsifylab alpha": {
            "falsifylab-alpha": {
                "command": "python",
                "args": [
                    "-m",
                    "falsifylab_alpha_mcp"
                ],
                "env": {
                    "FL_API_KEY": "fl_xxx"
                }
            }
        }
    }
}

From the repository

Install the package via pip (pip install falsifylab-alpha-mcp), then add the MCP server in your Claude Code config using claude mcp add with the FL_API_KEY environment variable, or define it in .mcp.json with the command python -m falsifylab_alpha_mcp. A free tier works without an API key; a Pro tier ($19/mo) requires a key from falsifylab.com/pro.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "falsifylab alpha": {
            "falsifylab-alpha": {
                "command": "python",
                "args": [
                    "-m",
                    "falsifylab_alpha_mcp"
                ],
                "env": {
                    "FL_API_KEY": "fl_xxx"
                }
            }
        }
    }
}

McpServers

{
    "falsifylab-alpha": {
        "command": "python",
        "args": [
            "-m",
            "falsifylab_alpha_mcp"
        ],
        "env": {
            "FL_API_KEY": "fl_xxx"
        }
    }
}

MCP data layer for AI-assisted market research.13 live finance tools that drop into Claude Code, Cursor, Cline, Windsurf, or any MCP-compatible client. Free tier requires no signup.

Not a signal service. Not investment advice. Public market data with light enrichment for AI agents. Backtest before acting.

Option 1: hosted MCP (zero install).Point your agent at the hosted endpoint, no Python needed.

{ "mcpServers": { "falsifylab-alpha": { "url": "https://mcp.falsifylab.com/" } } }

Free tier auto-applies. OAuth 2.1 + PKCE flow for paid plan via Whop. Streamable HTTP transport. Full OpenAPI 3.1 spec athttps://docs.falsifylab.com/openapi.html.

Zero runtime dependencies (Python stdlib only). Then wire to your agent. see client setup.

When the user asks your AI agent things like:

- "What insider clusters are forming today?"
- "Show me Hyperliquid vaults with sharp Sharpe and <10% drawdown"
- "Are BTC ETF flows confirming or diverging from price action?"
- "What's in the macro tape right now?"
- "Find Polymarket whales with 60%+ win rate"

...the agent calls one of 13 tools and grounds its answer in real-time numbers from public-market data — instead of speculating from training-data knowledge.

All tools have full JSON schemas exposed at /.well-known/mcp/server-card.json.

claude mcp add falsifylab-alpha -- python -m falsifylab_alpha_mcp

claude mcp add falsifylab-alpha \ --env FL_API_KEY=fl_your_key \ -- python -m falsifylab_alpha_mcp

Drop into~/.cursor/mcp.jsonor workspace root.mcp.json:

{ "mcpServers": { "falsifylab-alpha": { "command": "python", "args": ["-m", "falsifylab_alpha_mcp"], "env": { "FL_API_KEY": "fl_your_key_or_omit_for_free_tier" } } } }

Settings → MCP Servers → Add Server. Paste the same JSON as Cursor above.

Settings → MCP. Same JSON config. Auto-indexed from Smithery within 48h.

Connect via Smithery's hosted gateway — no local Python install needed. Seesmithery.ai/servers/falsifylab/falsifylab-alpha-mcp.

Use macro_tape. Show me SPX, VIX, BTC, ETH with 1d and 5d returns.

If the agent returns numbers, you're live.

Copy-paste these. They work on first run.

Use macro_tape. Tell me the macro regime in 3 sentences. Cite specific numbers — last price, 1d return, 5d return. Then list 2 tickers from sec8k_material_today that might benefit from this regime.

Run insider_buy_clusters (min_insiders=3) and sec8k_material_today (items=["2.02","8.01","5.02"]). Find tickers in both within 24h. For each match, summarize what insiders bought and what the 8-K said. End with the bear case in one sentence.

Use confluence_today with min_signals=2. For each asset/ticker, explain why these signals stacking is meaningful in 2 sentences. Skip noise (DeFi LP pools with stablecoins). Highlight the most contrarian stack.

8 more recipes atfalsifylab.com/cookbook.

Launch promoEARLY50: 50% off first 3 months, capped 25 redemptions. Get a key at falsifylab.com/pro.

Public agent calling these tools every 15 minutes:falsifylab.com/demo. Same MCP server you'd install. Real numbers, no curation.

Built it because the author hand-scraped SEC EDGAR and DefiLlama at 6am every morning to feed a fleet of trading bots. The bots that survived ate from this exact pipeline. Wrapped it as an MCP server so any agent can pull the same data.

The bot fleet receipts (alive + dead, P&L, drawdown) are public at falsifylab.com/vaults.

- What we do: aggregate + lightly enrich public market data, expose via MCP
- What we don't: trade execution, brokerage, advisory, signal selling
- Data sources: SEC EDGAR (Form 4, 8-K), SoSoValue (ETF flows), DefiLlama (yield), Hyperliquid public API, Polymarket public API, Yahoo Finance (macro)
- Privacy: free-tier key issued by hash(IP+UA), not stored long-term. Request bodies never logged.

The local stdio server writes minimal per-tool telemetry JSONL rows to:

- /var/log/falsifylab/mcp_tool_calls.jsonl(override withFL_MCP_TOOL_CALL_LOG)

- ts,tool,args_keys(argument names only),has_api_key,key_hash(sha256 prefix),version

- raw API keys
- argument values / request bodies
- IP address
- email / name / other user identifiers

- All 13 tools return live data inside agent calls under 1s p95.
- Free tier has zero signup friction. No API key needed for the cached path.
- Form 4 insider clusters get refreshed every 15 min on weekdays from SEC EDGAR direct, no 3rd-party reseller in the pipeline.
- DefiLlama yields are emissions-stripped (headline APY minus reward tokens), so a 200% farm and a 200% farm are not the same number any more.
- Hyperliquid vault NAV updates hit our R2 mirror within 60s of the source ticker.
- Telegram + Slack webhook delivery on Pro Plus is on-time within the cron window. No queue backups in the launch month.

- 8-K material filings list is empty over weekends because SEC does not file. Returnscount: 0Sat/Sun. Expected.
- Macro tape uses Yahoo Finance free endpoints. Intraday gap of 15-20 min during US market hours. We plan to swap for a paid feed at Teams tier, not before.
- onchain_smart_wallets only covers Solana right now. Base + Ethereum copy-trade scores are queued for v0.3.x.
- Free tier cache is 24h. Soconfluence_todayon a free key shows yesterday's confluence, not today's. Pro $19/mo plan hits live.
- Historical replay across multiple quarters is not in v0.2.x. Tracking as roadmap item.
- No SDK for TypeScript or Go yet. Python MCP server only. Use stdio transport from any MCP-compatible client meanwhile.

- Stripe Connect direct subscriptions (operator KYC blocker). Whop is the path.
- Substack paid plan (Stripe dependency).
- A previous package version 0.2.0 shipped a brokenapi.falsifylab.comhost. Fixed in 0.2.1 within 4 days. Apologies if you grabbed 0.2.0 first.

If you find something broken, dm the FL X account or open an issue. We ship fixes inside the same day for prod-blocking bugs.

your AI agent ↓ (MCP stdio) falsifylab_alpha_mcp (Python stdlib, no deps) ↓ (HTTPS) falsifylab.com/api/ (Cloudflare Workers) ↓ (cached 60s-1hr) R2 (data feeds refreshed every 15min via cron) ↓ (every 15min) Backend cron scripts (Form 4, 8-K, ETF, yield, polymarket, onchain, etc.)

Free tier hits cached data with 24h age. Pro tier hits the same endpoints with auth header, bypasses cache to fresh upstream.
- Live demo:falsifylab.com/demo
- Install guide:falsifylab.com/install
- Cookbook:falsifylab.com/cookbook
- Pricing:falsifylab.com/pro
- Comparison(vs Token Terminal / Nansen / Dune):falsifylab.com/vs
- MCP server card:/.well-known/mcp/server-card.json
- Substack:falsifylab.substack.com
- PyPI:pypi.org/project/falsifylab-alpha-mcp
- Smithery:smithery.ai/servers/falsifylab/falsifylab-alpha-mcp
- Agent starter repo:github.com/opsfalsifylab/falsifylab-agent-starter

- Issues:GitHub issues
- Email:ops@falsifylab.com
- Security: report to ops@falsifylab.comwith subject[security]. 48h response. Responsible disclosure credited in CHANGELOG.

- New tool ideas (open issue first to discuss scope)
- Documentation improvements
- Bug fixes

Do not submit PRs for trading-signal generators or copy-trading helpers — out of scope for this server (we are research data infrastructure, not advisory).

FalsifyLab Alpha v0.3.3 · Built for AI coding agents · Free tier no signup · falsifylab.com*

Remote MCP server for historical crypto & prediction-market data: search ~500K instruments, live market stats (OHLC, turnover, spreads, depth, slippage) and tick-data purchase. Keyless for catalog & stats; optional OAuth for account tools. Endpoint: https://cryptostruct.com/mcp

Read-only MCP server for your Evibe investment portfolio + live market data (holdings, performance, dividends, benchmarks, screeners). Works with Claude & ChatGPT.

Remote MCP server with real-money crypto casino audit data: trust scores, rankings, live payout tests, and T&C-decoded bonuses. No API key, Ed25519-signed answers. Endpoint: https://wagerx.io/mcp

Alpaca’s official MCP Server lets you trade stocks, ETFs, crypto, and options, run data analysis, and build strategies in plain English directly from your favorite LLM tools and IDEs

Live cross-DEX crypto prices read from on-chain pool state: per-venue price, liquidity depth and gross cross-venue spread across BSC, Polygon, Arbitrum, Base, Avalanche and Optimism. Works keyless, no account.

Bottom/top market-timing verdicts for 8 markets (crypto, stocks, commodities, FX, property) — x402 pay-per-call, no API key.

Read-only, sourced and timestamped prices for nine Binance Spot USDT markets through a public Streamable HTTP MCP endpoint.

Read-only crypto derivatives data for agents: funding, open interest, liquidations, options flow, COT, ETF flows, VPIN. 20 tools, no API key, hosted at https://mcp.bykaranteli.com

Pre-trade safety check for Solana tokens — traces coordinated wallet funding, same-block bundle buys and serial-launcher deployer history into one Exit-Liquidity Risk verdict before an agent buys.

Free crypto address labels. Identify known addresses on major networks with a free API.

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

Claude Desktop / Cursor

McpServers

Install

More like this

Sequential Thinking

Filesystem

EverArt

Google Drive

Reactive Resume

FastMCP v2 🚀