Fama-French Replicate Server

Overview

The Fama-French Replicate Server provides official Fama-French 5-factor daily data, replicated proxy factors from the hosted cache, and loadings / alpha estimation against factor returns.

Connection

Add this server to your MCP client configuration.

Cursor
Bearer auth

{
  "mcpServers": {
    "fama-french-replicate": {
      "url": "https://fama-french-factors-production.up.railway.app/mcp/fama_french_replicate"
    }
  }
}

{
  "mcpServers": {
    "fama-french-replicate": {
      "url": "https://fama-french-factors-production.up.railway.app/mcp/fama_french_replicate",
      "headers": {
        "Authorization": "Bearer ${env:FAMA_FRENCH_REPLICATE_MCP_TOKEN}"
      }
    }
  }
}

Restart the client after changing MCP configuration. The server tools appear automatically after the connection is established.

Transport

Property	Value
Protocol	MCP over Streamable HTTP
MCP URL	`https://fama-french-factors-production.up.railway.app/mcp/fama_french_replicate`
Health URL	`https://fama-french-factors-production.up.railway.app/health`
MCP path	`/mcp/fama_french_replicate`
Request envelope	`{"request": {...}}`
Auth	Optional bearer token when enabled for the endpoint

Best-Fit Workflows

Fetch official Fama-French factors.
Fetch replicated proxy factors from the hosted cache.
Fetch the latest available proxy factor row.
Regress returns on factor series to estimate loadings and alpha.

Recommended Tools

get-official-ff-factors
get-proxy-ff-factors
get-proxy-ff-factors-last
get-loadings-and-alpha

Tools

Tool	Description	Returns
`get-official-ff-factors`	Download and process Fama-French 5-factor research data.	`pd.DataFrame`
`get-proxy-ff-factors`	Fetch replicated (proxy) Fama-French 5-factor data computed by our internal methodology.	`pd.DataFrame`
`get-proxy-ff-factors-last`	Fetch replicated (proxy) Fama-French 5-factor data for the latest available trading date.	`pd.DataFrame`
`get-loadings-and-alpha`	Performs time-series regression of asset or portfolio returns on factor returns to estimate factor exposures (loadings) and abnormal returns (alpha). Returns a Series containing the estimated loadings and alpha. Params: factors: pd.DataFrame of factor returns (e.g., ‘MKT’, ‘SMB’, ‘HML’, ‘RMW’, ‘CMA’), rets: pd.Series of asset/portfolio excess returns, from_date/to_date: optional date range filters (e.g., ‘2020-01-01’)	`pd.Series`

Examples

Fetch official factors

{
  "request": {
    "from_date": "2024-01-01",
    "to_date": "2024-12-31"
  }
}

Fetch proxy factors

{
  "request": {
    "from_date": "2026-04-01",
    "to_date": "2026-04-21"
  }
}

Fetch the latest proxy row

{
  "request": {}
}

Estimate loadings and alpha

{
  "request": {
    "factors": "$last",
    "rets": "$prev",
    "from_date": "2024-01-01",
    "to_date": "2024-12-31"
  }
}

n8n Workflow

This server is a good fit for an n8n report workflow with a Manual Trigger, Schedule Trigger, or POST Webhook. Use n8n to normalize portfolio input, call MCP tools, and deliver the final report as webhook JSON, an execution log, email, or chat notification. Recommended n8n MCP chain:

Accept a portfolio through a Webhook or manual configuration.
Call get-proxy-ff-factors for the factor window.
Call get-loadings-and-alpha for each asset or aggregated portfolio return series.
If a tool returns result_id, call result_get before assembling the report.
Route the output to Respond to Webhook or delivery nodes.

Keep delivery credentials in n8n Credentials or environment variables. Do not export API keys, bot credentials, credential IDs, email recipients, or private webhook paths with the workflow. See n8n Workflows for the shared webhook and MCP session patterns. Available n8n templates:

Factor Loading Report JSON - public CSV portfolio webhook at POST https://n8n.limex.pro/webhook/ff-factor-loading-report.
Extended Factor Loading Report JSON - import-only template for manual, scheduled, Lime, and delivery use cases. The live webhook is not published.

Notes

Proxy-factor tools read from the hosted factor cache.
Use Dataloader when you need raw OHLCV data rather than factor data.

Client setup

Configure this endpoint in Cursor, Claude Desktop, or a generic MCP client.

n8n workflows

Build webhook and scheduled reporting flows around this MCP endpoint.

Shared tools

Use health, result, artifact, environment, and table helper tools.

Other Servers

Dataloader

Market-data retrieval, TA-Lib indicators, and dataframe exports.

Statistical Factor Models

Stock-Watson, complete-panel, and dynamic statistical factor extraction.

Jump Models

JumpModel and SparseJumpModel regime fitting, online prediction, and backtesting.

Wavelet Mean Reversion

Wavelet-based mean reversion analysis for financial time series.

Parallax ExtremeHurst

ExtremeHurst signal generation from OHLCV data.

EP Ratio Screener

Fundamental stock screening based on earnings yield and balance-sheet quality.

Volatility Scaling Lab

Volatility targeting, EWMA volatility, Monte Carlo bands, and risk diagnostics.

Overview

MCP Setup

Dataloader Server